© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 129805
    Prev
    Next
    INDEX
    Explanations

    plant

    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
    💙
    -0.08
    涨停
    -0.07
    ijing
    -0.07
    各自的
    -0.07
    liquid
    -0.07
    before
    -0.07
    欧式
    -0.07
    obsolete
    -0.07
    (org
    -0.07
    ritos
    -0.07
    POSITIVE LOGITS
    acr
    0.08
    惭
    0.07
    ⽊
    0.07
    ﰴ
    0.06
     Sherman
    0.06
     Faculty
    0.06
     hã
    0.06
    谦
    0.06
     textField
    0.06
    垱
    0.06
    Activations Density 0.012%

    No Known Activations