© 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. 78956
    Prev
    Next
    INDEX
    Explanations

    lap

    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
     Substance
    -0.07
    /&
    -0.07
    桢
    -0.07
    ngo
    -0.07
    (photo
    -0.07
     pizza
    -0.07
    ('[
    -0.07
    -length
    -0.07
    /plugins
    -0.07
     pregnant
    -0.06
    POSITIVE LOGITS
    蚜
    0.07
    足足
    0.07
     ability
    0.07
    day
    0.07
     يت
    0.07
    蟹
    0.07
     двигател
    0.07
     well
    0.07
     JFactory
    0.07
     getProperty
    0.07
    Activations Density 0.049%

    No Known Activations