© 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. 7429
    Prev
    Next
    INDEX
    Explanations

    specifying categories and types

    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
    ä¸Ģ家
    -0.10
    第ä¸ī个
    -0.09
    å®ľ
    -0.09
    _THIS
    -0.09
    byn
    -0.09
    æ·ij
    -0.08
    .OP
    -0.08
    zcze
    -0.08
    åı¦ä¸Ģä½į
    -0.08
    æĽ³
    -0.08
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.20
    åĪĨåĪ«ä¸º
    0.19
    è´¨éĩıåĴĮ
    0.16
    è¿Ļ两个
    0.16
    æĸĩåĮĸåĴĮ
    0.15
    ä¼ģä¸ļåĴĮ
    0.15
    æŶéĹ´åĴĮ
    0.15
    ç»ıéªĮåĴĮ
    0.14
    两ç§į
    0.14
    èĥ½åĬĽåĴĮ
    0.14
    Activations Density 0.403%

    No Known Activations