© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15-RESID-POST-AA
    11. 49605
    Prev
    Next
    INDEX
    Explanations

    editing existing text

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITER
    -0.07
     spanning
    -0.07
     grayscale
    -0.07
    大奖
    -0.06
     uppercase
    -0.06
    ༚
    -0.06
     Centers
    -0.06
    (dtype
    -0.06
     umbrella
    -0.06
    RootElement
    -0.06
    POSITIVE LOGITS
     orders
    0.07
     Kısa
    0.07
    吃得
    0.07
     לוקח
    0.06
    .)
    0.06
    iking
    0.06
     fucking
    0.06
    먹
    0.06
    Ǐ
    0.06
     الو
    0.06
    Activations Density 0.005%

    No Known Activations