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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 10942
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    licted
    -0.08
     לעומ
    -0.07
    _avail
    -0.07
     rumours
    -0.06
     ```
    -0.06
    CompanyId
    -0.06
    了一口
    -0.06
    变更
    -0.06
     spo
    -0.06
     respawn
    -0.06
    POSITIVE LOGITS
    旨在
    0.07
    \M
    0.07
     TR
    0.07
     lesson
    0.07
     TypeError
    0.07
    .transitions
    0.06
    .Meta
    0.06
     иностран
    0.06
     Ultra
    0.06
     vagy
    0.06
    Activations Density 0.022%

    No Known Activations