© 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. 56163
    Prev
    Next
    INDEX
    Explanations

    ice cream

    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
    é»İæĺİ
    -0.10
    çļĦåij³éģĵ
    -0.09
    åĨ°åĨ·
    -0.09
    .tools
    -0.09
    .COL
    -0.08
    æ¯Ľ
    -0.08
    kas
    -0.08
    é¢ĦçķĻ
    -0.08
    çŁ¥æĥħ
    -0.08
    åı¯è¡Į
    -0.08
    POSITIVE LOGITS
    ç«ŀ
    0.10
    æŶéĹ´åĨħ
    0.09
    为æĤ¨
    0.09
    è®Ń
    0.08
    ç±³é¥Ń
    0.08
    otch
    0.08
    oger
    0.08
    èĿ¾
    0.08
    åįĪé¤IJ
    0.08
    å®īåħ¨äºĭæķħ
    0.08
    Activations Density 0.009%

    No Known Activations