© 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 EvalsExportsAPI 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. 85663
    Prev
    Next
    INDEX
    Explanations

    "

    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
     garant
    -0.07
     Dod
    -0.07
    冬季
    -0.07
    Done
    -0.07
    治安
    -0.07
    得罪
    -0.07
    WINDOW
    -0.07
     Annual
    -0.07
     gez
    -0.07
     termination
    -0.07
    POSITIVE LOGITS
    web
    0.07
    doctype
    0.07
    _hours
    0.07
    developer
    0.07
    상
    0.07
    عبة
    0.07
     Depths
    0.07
     optimism
    0.06
    星
    0.06
    🎱
    0.06
    Activations Density 0.007%

    No Known Activations