© 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. 22559
    Prev
    Next
    INDEX
    Explanations

    giving or handing something

    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
    æĤ¬å¿µ
    -0.10
     deposit
    -0.09
    æĹłäºº
    -0.09
    .Constraint
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
     Equip
    -0.09
    ember
    -0.09
    åŃ
    -0.09
    _dispatch
    -0.08
    å¿Ĵ
    -0.08
    POSITIVE LOGITS
    éĢĴç»Ļ
    0.11
     ÑĤоÑĢ
    0.09
     handed
    0.09
    æĹĮ
    0.09
    è®°èĢħéĩĩ访
    0.08
    rejected
    0.08
    æı´
    0.08
    jem
    0.08
    è¿ĩæĿ¥
    0.08
    FetchRequest
    0.08
    Activations Density 0.025%

    No Known Activations