© 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. 17930
    Prev
    Next
    INDEX
    Explanations

    . followed by initials

    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
    æī«ä¸Ģæī«
    -0.09
    apur
    -0.09
    uci
    -0.09
     ÑģебÑı
    -0.09
    åĮĻ
    -0.09
    dorf
    -0.09
    åħļå·¥å§Ķ
    -0.08
    (ERR
    -0.08
    stdout
    -0.08
    åĹij
    -0.08
    POSITIVE LOGITS
    çĪº
    0.09
     BP
    0.09
    nof
    0.09
    é£İçŃĿ
    0.08
    pec
    0.08
    chema
    0.08
    BP
    0.08
    åģļ大
    0.08
     ÑĢаз
    0.08
    ÅĽ
    0.08
    Activations Density 0.048%

    No Known Activations