© 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. 22921
    Prev
    Next
    INDEX
    Explanations

    thioester compounds

    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
    -mini
    -0.09
     verifier
    -0.08
     Gib
    -0.08
     Mini
    -0.08
    .instant
    -0.08
    Stride
    -0.08
     mini
    -0.08
     cánh
    -0.07
    å°ıåŀĭ
    -0.07
    Mad
    -0.07
    POSITIVE LOGITS
    èŁł
    0.11
    ç»Ħç»ĩå®ŀæĸ½
    0.11
    ç¦ıå¾·
    0.10
    æİĴ污
    0.09
    鸣
    0.09
    æ¤Ĵ
    0.09
    ç»Īæŀģ
    0.09
    èĻ¢
    0.09
    ооÑĢ
    0.09
    æĬķèµĦåŁºéĩij
    0.09
    Activations Density 0.224%

    No Known Activations