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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76357
    Prev
    Next
    INDEX
    Explanations

    explicit pornographic content and adult-site promotional text, especially titles and graphic descriptions of sexual acts.

    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
     desarrollo
    -0.08
    Reducers
    -0.08
     invites
    -0.07
    .MouseAdapter
    -0.07
    签订了
    -0.07
    生机
    -0.07
    временно
    -0.07
     karşı
    -0.06
     rencontrer
    -0.06
     combineReducers
    -0.06
    POSITIVE LOGITS
    学问
    0.07
    명
    0.06
    _date
    0.06
    tal
    0.06
    _wire
    0.06
     *)[
    0.06
     '<?
    0.06
    _COMBO
    0.06
    dbName
    0.06
    용
    0.06
    Activations Density 0.095%

    No Known Activations