© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19694
    Prev
    Next
    INDEX
    Explanations

    discussions and questions

    np_max-act · gemini-2.0-flash

    abstract head nouns in prompts that denote requested categories or evaluative criteria—indicating list/summary requests, often in “X of Y” constructions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    述职
    -0.07
    연
    -0.07
     License
    -0.07
    セ
    -0.07
    ipe
    -0.07
     fire
    -0.07
    SELL
    -0.06
    不舍
    -0.06
    subsection
    -0.06
    ἢ
    -0.06
    POSITIVE LOGITS
    Moment
    0.09
    أور
    0.08
    Box
    0.08
    看来
    0.07
    _SLEEP
    0.07
    FY
    0.07
    とともに
    0.07
    \admin
    0.07
    bos
    0.07
    滚动
    0.07
    Activations Density 0.289%

    No Known Activations