© 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. 112012
    Prev
    Next
    INDEX
    Explanations

    pathology/cells

    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
     striped
    -0.07
    投资额
    -0.07
     traced
    -0.07
    _advanced
    -0.07
     updater
    -0.07
    _CPP
    -0.07
    루
    -0.07
    Directions
    -0.07
     UPPER
    -0.07
    	head
    -0.07
    POSITIVE LOGITS
    ('.')[
    0.07
    ynec
    0.07
    안
    0.07
    (".")
    0.07
    ᴖ
    0.07
     schön
    0.07
    مير
    0.07
    묻
    0.06
    vana
    0.06
    $txt
    0.06
    Activations Density 0.018%

    No Known Activations