© 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. 22960
    Prev
    Next
    INDEX
    Explanations

    dates following "on"

    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
    è¿¢
    -0.10
    两年åīį
    -0.09
    éĢ¾
    -0.09
    æį¢æĿ¥
    -0.09
    æ¯ıå¹´éĥ½
    -0.09
    è¿Ļ项
    -0.08
    _NOP
    -0.08
    abis
    -0.08
    妳
    -0.08
    nap
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.12
    (crate
    0.10
    诸å¦Ĥ
    0.09
    éĺ´
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    çĶ°
    0.08
    td
    0.08
    ä¸įåı¯æĪĸ缺
    0.08
     TBD
    0.08
    åīįæīĢ
    0.08
    Activations Density 0.202%

    No Known Activations