© 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. 54080
    Prev
    Next
    INDEX
    Explanations

    heat, cook, melt

    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
    æıŃ
    -0.09
    lico
    -0.09
    erring
    -0.09
    éĿ¢åŃIJ
    -0.08
     tier
    -0.08
    enos
    -0.08
    æ¡£æ¡Ī
    -0.08
    tier
    -0.08
    éĿ¢å®¹
    -0.08
    æľªæĿ¥åıijå±ķ
    -0.08
    POSITIVE LOGITS
    缴èĩ³
    0.10
    æģª
    0.10
    æµĵ缩
    0.10
    elts
    0.09
    unate
    0.09
    ä¸ĸçķĮç»ıæµİ
    0.09
    åĤį
    0.09
    æĶ¶ç´§
    0.09
    ToFit
    0.09
    ãģ»ãģ¨
    0.08
    Activations Density 0.013%

    No Known Activations