© 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. 7-RESID-POST-AA
    11. 38554
    Prev
    Next
    INDEX
    Explanations

    quoted

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    作
    -0.07
    יז
    -0.07
    ж
    -0.07
     ổ
    -0.07
    友好
    -0.07
    一体
    -0.06
    飞行
    -0.06
     insect
    -0.06
    uste
    -0.06
    토
    -0.06
    POSITIVE LOGITS
     shortcomings
    0.08
    尽量
    0.08
     Leather
    0.07
     quoted
    0.07
    0.07
    grades
    0.07
     allerdings
    0.07
     Parenthood
    0.07
    <Scalars
    0.07
     Colombia
    0.07
    Activations Density 0.004%

    No Known Activations