© 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. 33312
    Prev
    Next
    INDEX
    Explanations

    describing appearance or state

    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
    æĥ³ä¸įåĪ°
    -0.11
    è§ģè¯ģ
    -0.10
    nesia
    -0.10
    è§ģè¯ģäºĨ
    -0.10
     witness
    -0.09
     witnessing
    -0.09
    çī¢çī¢
    -0.09
    .unregister
    -0.09
     witnessed
    -0.09
     Witness
    -0.09
    POSITIVE LOGITS
    çļĦæł·åŃIJ
    0.11
    å®ł
    0.09
    è¡Ĺ头
    0.08
    ä¸įåħį
    0.08
    å¾Īæĥ³
    0.08
    å¼ĢåѦ
    0.08
    æł·åŃIJ
    0.08
    寵
    0.08
    åıijå±ķåīįæĻ¯
    0.08
    å¸
    0.08
    Activations Density 0.053%

    No Known Activations