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. 71694
    Prev
    Next
    INDEX
    Explanations

    destruction

    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
     popul
    -0.07
    יפים
    -0.07
    .Active
    -0.07
    INATION
    -0.07
     går
    -0.07
    [item
    -0.07
    🇦
    -0.07
     Aless
    -0.07
    ∉
    -0.07
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.07
    POSITIVE LOGITS
    串
    0.07
     funded
    0.07
     erotische
    0.07
     Ltd
    0.07
    每年都
    0.07
     attend
    0.07
     tamaño
    0.07
    システ
    0.07
    搜集
    0.07
     scrutin
    0.07
    Activations Density 1.114%

    No Known Activations