Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 88291
    Prev
    Next
    INDEX
    Explanations

    type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _syn
    -0.07
    会出现
    -0.07
    育
    -0.07
    ♎
    -0.07
    恐怖
    -0.07
    危险
    -0.07
    一種
    -0.07
    ニ
    -0.07
    大概是
    -0.07
     addition
    -0.07
    POSITIVE LOGITS
     القر
    0.08
    \model
    0.08
    _Component
    0.07
     высоко
    0.07
    メン
    0.07
    呸
    0.07
    _LOW
    0.07
     tuo
    0.07
    _eof
    0.07
    �
    0.07
    Activations Density 0.002%

    No Known Activations