© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 22557
    Prev
    Next
    INDEX
    Explanations

    slick

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currentPage
    -0.07
    产业园
    -0.07
    ubar
    -0.07
    Jesteś
    -0.07
    bdb
    -0.07
    jf
    -0.07
    到现在
    -0.07
    探索
    -0.07
    Es
    -0.07
    苯
    -0.06
    POSITIVE LOGITS
    惯例
    0.08
     directive
    0.08
     tight
    0.07
     التى
    0.07
    .ta
    0.07
     allerdings
    0.07
    /javascript
    0.07
     Patterson
    0.07
     раств
    0.07
     attorney
    0.07
    Activations Density 0.001%

    No Known Activations