© 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
    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. 24786
    Prev
    Next
    INDEX
    Explanations

    oocytes

    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
    unwrap
    -0.07
     Fuller
    -0.07
    -year
    -0.07
    alignment
    -0.07
     +'
    -0.07
     hollow
    -0.07
    enabled
    -0.07
    Oops
    -0.07
    讷
    -0.07
     scored
    -0.07
    POSITIVE LOGITS
     세
    0.07
    裎
    0.07
    ቢ
    0.07
    酿
    0.06
    奢侈品
    0.06
    تبع
    0.06
     воздействи
    0.06
    шедш
    0.06
     Morm
    0.06
     habits
    0.06
    Activations Density 0.001%

    No Known Activations