© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19408
    Prev
    Next
    INDEX
    Explanations

    box/sidebar/container elements

    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
     intent
    -0.08
    é¹ħ
    -0.08
    éĻª
    -0.07
    èı©æıIJ
    -0.07
     Pump
    -0.07
     Sale
    -0.07
    åľ¨ç¾İåĽ½
    -0.07
    ä¸įçķĻ
    -0.07
     Paren
    -0.07
     trần
    -0.07
    POSITIVE LOGITS
    ä¸ĵæłı
    0.12
     siden
    0.10
    SID
    0.10
    æĥ³çŁ¥éģĵ
    0.10
    羣åģĩ
    0.10
    obox
    0.09
    amarin
    0.09
    /manual
    0.09
    è¿Ļä¸įæĺ¯
    0.09
     maté
    0.09
    Activations Density 0.053%

    No Known Activations