© 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. 62077
    Prev
    Next
    INDEX
    Explanations

    heating and temperature

    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
    鸳
    -0.10
    éľ²å¤©
    -0.09
    å¤ĸéĿ¢
    -0.09
    change
    -0.09
    å¤ĸåĽ´
    -0.09
    mul
    -0.09
    é¹Ħ
    -0.08
    è¿ijæľŁ
    -0.08
    wor
    -0.08
    lik
    -0.08
    POSITIVE LOGITS
    åĶ§
    0.10
    以èĩ´
    0.10
    åĴĮå®ĮåĸĦ
    0.09
    æ¾Ħæ¸ħ
    0.09
    èµ·æĿ¥
    0.09
    æ°´ä¸Ń
    0.09
    LogLevel
    0.08
    é¢ł
    0.08
    Operand
    0.08
    以èĩ³äºİ
    0.08
    Activations Density 0.008%

    No Known Activations