© 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. 17778
    Prev
    Next
    INDEX
    Explanations

    search and filters

    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
    åħ¸åŀĭæ¡Īä¾ĭ
    -0.09
    à¸Ĥาà¸Ķ
    -0.08
    åħ¸åŀĭçļĦ
    -0.08
    å²ļ
    -0.08
    åIJ¬åIJ¬
    -0.08
    discord
    -0.08
    è°Īè°Ī
    -0.08
    .opensource
    -0.08
    åħ¨å®¶
    -0.07
    è®®
    -0.07
    POSITIVE LOGITS
     search
    0.14
    æIJľç´¢
    0.13
    è¿ĩ滤
    0.12
    _SEARCH
    0.12
    çŃĽæŁ¥
    0.11
    .search
    0.11
     filters
    0.11
    	search
    0.11
    çŃĽéĢī
    0.11
    _search
    0.11
    Activations Density 0.136%

    No Known Activations