© 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. 11-RESID-POST-AA
    11. 2625
    Prev
    Next
    INDEX
    Explanations

    readline

    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
    숩
    -0.08
    解放思想
    -0.07
    �
    -0.07
    䋌
    -0.07
     RelativeLayout
    -0.07
    �
    -0.07
     заболевания
    -0.06
     않을
    -0.06
     placed
    -0.06
     contemplating
    -0.06
    POSITIVE LOGITS
     onion
    0.08
    اش
    0.08
    鼎
    0.07
    גי
    0.07
    WND
    0.07
    mic
    0.07
    fire
    0.07
    -fi
    0.07
    ony
    0.07
    atl
    0.07
    Activations Density 0.006%

    No Known Activations