© 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. 2133
    Prev
    Next
    INDEX
    Explanations

    legal jurisdiction

    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
    -align
    -0.07
    跳跃
    -0.06
    のような
    -0.06
     aws
    -0.06
    .getObject
    -0.06
     lacks
    -0.06
    share
    -0.06
     look
    -0.06
    >>,↵
    -0.06
    اختلاف
    -0.06
    POSITIVE LOGITS
    遐
    0.08
    .notNull
    0.07
     Authorized
    0.07
    .modules
    0.07
    (priv
    0.07
    힛
    0.07
     Wein
    0.07
    =key
    0.06
    뻣
    0.06
     בו
    0.06
    Activations Density 0.012%

    No Known Activations