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. 36136
    Prev
    Next
    INDEX
    Explanations

    icon, url

    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
    fon
    -0.08
     самого
    -0.07
    ún
    -0.07
    ﯹ
    -0.06
     ogó
    -0.06
     nuevos
    -0.06
    耏
    -0.06
     düzenleme
    -0.06
     취
    -0.06
    畴
    -0.06
    POSITIVE LOGITS
     payload
    0.07
     Sacred
    0.07
    渗
    0.07
    beat
    0.07
     pretty
    0.07
    _agents
    0.07
     enfants
    0.07
    sharp
    0.07
     актив
    0.07
     '-';↵
    0.06
    Activations Density 0.003%

    No Known Activations