© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23069
    Prev
    Next
    INDEX
    Explanations

    Hawkins, Edwards, Coutin, Nakayama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usi
    -0.10
    оÑĩек
    -0.10
    iates
    -0.09
    oha
    -0.09
     Highlander
    -0.09
    atan
    -0.09
    箫
    -0.08
    uell
    -0.08
    Sci
    -0.08
    pery
    -0.08
    POSITIVE LOGITS
    atic
    0.10
    麽
    0.10
    ael
    0.10
    Ī
    0.10
    er
    0.09
     nghiá»ĩm
    0.09
    lder
    0.09
    ูà¹Ī
    0.08
    dre
    0.08
    gmt
    0.08
    Activations Density 0.211%

    No Known Activations