© 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. 58177
    Prev
    Next
    INDEX
    Explanations

    running

    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
    å¾·æĭī
    -0.11
    æ§ģ
    -0.10
    éĸī
    -0.10
    าà¸ģ
    -0.10
    æ»ŀ
    -0.09
     اÙĦÙħÙĩ
    -0.09
    ouncy
    -0.09
    ç»Ī
    -0.09
     antenn
    -0.09
    åĥļ
    -0.09
    POSITIVE LOGITS
    æŃ¥è¡Į
    0.16
    è·ijæŃ¥
    0.15
    å¾ĴæŃ¥
    0.14
    èµ°è·¯
    0.13
     walk
    0.11
     walking
    0.10
    æŃ©ãģĦãģ¦
    0.10
    è¡Įèµ°
    0.10
    Walking
    0.10
    漫æŃ¥
    0.10
    Activations Density 0.243%

    No Known Activations