© 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. 61965
    Prev
    Next
    INDEX
    Explanations

    competition

    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
     rÃłng
    -0.10
    éĻħ
    -0.09
    fov
    -0.09
    ward
    -0.09
    ings
    -0.09
    OfFile
    -0.09
    pot
    -0.09
    uary
    -0.08
    ments
    -0.08
    IRST
    -0.08
    POSITIVE LOGITS
    aire
    0.12
    bero
    0.10
    ç»ĵæĿŁåIJİ
    0.10
    аÑĢÑĤ
    0.10
    æĿ¥ä¸´
    0.10
    çĻ½é¢Ĩ
    0.09
    ós
    0.09
    AIR
    0.09
    rze
    0.09
    ÑĢÑİ
    0.08
    Activations Density 0.015%

    No Known Activations