© 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. 34745
    Prev
    Next
    INDEX
    Explanations

    reason or cause

    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
     Ris
    -0.08
    æ´¾
    -0.08
    åĪĨ辨
    -0.08
    lide
    -0.08
    åIJĦåľ°
    -0.08
     Ñģли
    -0.08
    èķ¾
    -0.08
    è´Łè´£åIJĮå¿Ĺ
    -0.08
     Alternate
    -0.08
    (todo
    -0.08
    POSITIVE LOGITS
    éĻŁ
    0.11
    诸å¦Ĥ
    0.11
    yte
    0.10
    éĥ½ä¸įèĥ½
    0.10
    éĶĻè¿ĩäºĨ
    0.09
    é²ij
    0.09
    ç§įç§į
    0.09
    /ge
    0.09
    请åģĩ
    0.09
    éĥ½æĹłæ³ķ
    0.09
    Activations Density 0.026%

    No Known Activations