© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36324
    Prev
    Next
    INDEX
    Explanations

    below or in

    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
    ACHED
    -0.09
     Ñģебе
    -0.09
    罡
    -0.09
    æľĽåİ»
    -0.09
    ãĤĴå¾Ĺ
    -0.09
    ooled
    -0.08
    å¹´å¼Ģå§ĭ
    -0.08
    åĬŀ好
    -0.08
    é«ĺçŃīéĻ¢æł¡
    -0.08
    .HasValue
    -0.08
    POSITIVE LOGITS
    书ä¸Ń
    0.09
    è·Ľ
    0.09
    åĩĮ
    0.08
    æĸĩä¸Ń
    0.08
    Lng
    0.08
    ç¼¥
    0.08
    毯
    0.08
    inq
    0.08
    èħ´
    0.08
    uality
    0.07
    Activations Density 0.097%

    No Known Activations