© 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. 76006
    Prev
    Next
    INDEX
    Explanations

    celestial

    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
     twists
    -0.08
     Erica
    -0.08
     Marcus
    -0.07
     equ
    -0.07
    <long
    -0.07
     titan
    -0.07
    どのように
    -0.07
    DI
    -0.07
    没有任何
    -0.07
     newPosition
    -0.07
    POSITIVE LOGITS
     —↵↵
    0.06
     fandom
    0.06
    rawer
    0.06
     Age
    0.06
    日本の
    0.06
    𬸚
    0.06
     sets
    0.06
    ав
    0.06
    aint
    0.06
     çalışm
    0.06
    Activations Density 0.004%

    No Known Activations