© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32824
    Prev
    Next
    INDEX
    Explanations

    will be

    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¦ģè¿Ľä¸ĢæŃ¥
    -0.12
    ç«ĭåľº
    -0.10
    è¦ģåĬłå¼º
    -0.10
    ä¼ļè§īå¾Ĺ
    -0.09
    pill
    -0.09
     Äijang
    -0.09
    è¦ģåıĬæĹ¶
    -0.09
    åĬłåĢį
    -0.08
    òa
    -0.08
    æİĴåIJį第
    -0.08
    POSITIVE LOGITS
    ENA
    0.10
    大æ¦Ĥ
    0.09
    èĽĽ
    0.08
    使æĪij
    0.08
    estroy
    0.08
    使å¾Ĺ
    0.08
    æĺ¯éĿŀ
    0.08
    çŀĦ
    0.08
    ausible
    0.08
    è¿ĻåIJį
    0.08
    Activations Density 0.058%

    No Known Activations