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. 129632
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    dog
    -0.08
    <?,
    -0.07
    _contin
    -0.07
    镄
    -0.07
    帰り
    -0.07
     Loaded
    -0.06
    メリ
    -0.06
    容
    -0.06
     Constr
    -0.06
    specific
    -0.06
    POSITIVE LOGITS
    ewith
    0.08
     Haupt
    0.08
    .emptyList
    0.08
     "->
    0.07
    _rhs
    0.07
    _filepath
    0.07
    ------------------------------------------------------------------------------------------------
    0.07
    Meanwhile
    0.07
     sqrt
    0.07
    _r
    0.07
    Activations Density 0.001%

    No Known Activations