© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 10856
    Prev
    Next
    INDEX
    Explanations

    it was

    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
    hä
    -0.08
    è¿«ä¸įåıĬå¾ħ
    -0.08
    è§ģåΰ
    -0.08
    ç«Ļåľ¨
    -0.08
    éĶĭ
    -0.08
    å¾Ģä¸ĭ
    -0.08
    ä¸įçĽ¸ä¿¡
    -0.08
    æľĢçµĤ
    -0.08
     otherwise
    -0.08
    Chance
    -0.08
    POSITIVE LOGITS
    çĸ½
    0.10
    çļĦç¡®
    0.10
    ä¸į管æĺ¯
    0.09
    éªĭ
    0.09
    afil
    0.09
    çļĦç¡®æĺ¯
    0.09
    æĹłè®ºæĺ¯
    0.09
    è·Ĺ
    0.09
    ç¡®å®ŀ
    0.09
    eker
    0.08
    Activations Density 0.198%

    No Known Activations