© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 44960
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    programming code snippets and syntax within technical Q&A posts, especially C-like pointer/manipulation code and other embedded source code blocks.

    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
    DC
    -0.07
    술
    -0.07
    ive
    -0.07
    <a
    -0.06
     curve
    -0.06
    DP
    -0.06
     Mc
    -0.06
    .line
    -0.06
     Visit
    -0.06
    /work
    -0.06
    POSITIVE LOGITS
    好み
    0.08
    _strings
    0.07
     Staten
    0.07
    暂时
    0.07
    西域
    0.07
    ammable
    0.07
    pegawai
    0.07
    NIL
    0.07
     transitional
    0.07
     '*',
    0.06
    Activations Density 0.644%

    No Known Activations