© 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. 57286
    Prev
    Next
    INDEX
    Explanations

    off-season periods

    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
    æĪ´ä¸Ĭ
    -0.10
    åĢĴåľ¨
    -0.10
    æ¡Ĩ
    -0.09
    å¿ĺ
    -0.09
    _epsilon
    -0.09
    oya
    -0.09
    æľºéģĩ
    -0.09
    æĻĮ
    -0.09
    .epsilon
    -0.09
     pill
    -0.09
    POSITIVE LOGITS
    åĢĭ人
    0.10
    IFO
    0.09
    ICY
    0.09
    è¿ĺ好
    0.09
    ocha
    0.09
    icy
    0.08
    aries
    0.08
     andre
    0.08
    个人
    0.08
    å¯Ħæīĺ
    0.08
    Activations Density 0.016%

    No Known Activations