© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 59439
    Prev
    Next
    INDEX
    Explanations

    portion

    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
    ,g
    -0.07
     Glow
    -0.07
     Grow
    -0.07
    딛
    -0.07
     redo
    -0.07
    拢
    -0.06
                  
    ↵
    -0.06
     Jetzt
    -0.06
    ด
    -0.06
    w
    -0.06
    POSITIVE LOGITS
     portion
    0.09
    ียง
    0.07
     Phantom
    0.07
    LocalizedMessage
    0.07
    _ATTACHMENT
    0.07
    部件
    0.07
     authenticated
    0.07
     Pharmac
    0.07
     whe
    0.07
     traders
    0.07
    Activations Density 0.012%

    No Known Activations