© 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. 55668
    Prev
    Next
    INDEX
    Explanations

    depurination

    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
    yte
    -0.09
    lut
    -0.08
     FIG
    -0.08
    æĪij个人
    -0.08
     “
    -0.08
    åĨįæĿ¥
    -0.08
    åĩłä¹İæĺ¯
    -0.08
    å½ĵçĦ¶
    -0.07
    ParseException
    -0.07
     Figure
    -0.07
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.11
    å®ŀè·µä¸Ń
    0.10
    éĢļè¿ĩ对
    0.10
    åįĵ
    0.09
    缮çļĦåľ¨äºİ
    0.09
    RATION
    0.09
    æļ¨
    0.08
    ç±į
    0.08
    _bug
    0.08
    éĶ¦æłĩ
    0.08
    Activations Density 3.850%

    No Known Activations