© 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. 75319
    Prev
    Next
    INDEX
    Explanations

    _constraint

    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
    取出
    -0.08
    꺠
    -0.07
    挦
    -0.07
     massasje
    -0.07
    소
    -0.07
    ☚
    -0.07
     nakne
    -0.07
    手机版
    -0.07
     thaimassage
    -0.07
    张先生
    -0.06
    POSITIVE LOGITS
     دون
    0.09
    יאל
    0.07
    (weights
    0.07
    REDIT
    0.07
    人们
    0.07
    荣
    0.07
     الجميع
    0.07
     ,↵
    0.07
     plumbing
    0.07
     profound
    0.07
    Activations Density 0.007%

    No Known Activations