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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 41621
    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
    ainting
    -0.07
    聽
    -0.07
     Pip
    -0.07
    虽
    -0.07
    irty
    -0.07
    雖
    -0.07
    שתי
    -0.07
    咐
    -0.07
    תר
    -0.07
    显示器
    -0.07
    POSITIVE LOGITS
    职业生涯
    0.06
     בחיים
    0.06
     düzey
    0.06
    _LEVEL
    0.06
    踞
    0.06
     loop
    0.06
     pelic
    0.06
     QUICK
    0.06
     orderby
    0.06
     dönemin
    0.06
    Activations Density 0.002%

    No Known Activations