© 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. 4213
    Prev
    Next
    INDEX
    Explanations

    periods, halves, or sets

    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
    æĺİå¹´
    -0.09
    sus
    -0.09
    åľ¨å½ĵåľ°
    -0.09
    ppe
    -0.08
    æ¼¾
    -0.08
    åĽŀæĬ¥
    -0.08
    .GetSize
    -0.08
    ivid
    -0.08
     CFG
    -0.08
    .userData
    -0.07
    POSITIVE LOGITS
    ä¸Ģ段
    0.12
    ä¸ĭåįĬ
    0.11
    段
    0.11
    æĹ¶æ®µ
    0.11
    åŁ¤
    0.11
    ä¸ĭåįĬåľº
    0.11
    è¿Ļ段
    0.10
     Pandora
    0.10
    åįĬ个å°ıæŶ
    0.10
     Äijoạn
    0.10
    Activations Density 0.160%

    No Known Activations