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. 48358
    Prev
    Next
    INDEX
    Explanations

    ent

    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
    doesn
    -0.07
    Dice
    -0.07
     ail
    -0.07
     __('
    -0.07
     avons
    -0.07
     shooting
    -0.07
     Assad
    -0.07
     автомоб
    -0.07
    🏋
    -0.06
     aspir
    -0.06
    POSITIVE LOGITS
     Klo
    0.07
    丰富多彩
    0.07
    也只有
    0.07
    },
    0.06
     Integrated
    0.06
     normals
    0.06
     Vari
    0.06
    itat
    0.06
    "),
    0.06
    'utilisateur
    0.06
    Activations Density 0.176%

    No Known Activations