© 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. 30141
    Prev
    Next
    INDEX
    Explanations

    keloid disease, location names, heaters

    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
    èĢģ人家
    -0.10
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.09
    æĪij们çİ°åľ¨
    -0.09
    ä¸ŃåĽ½æĶ¿åºľ
    -0.08
    åĪ«äººçļĦ
    -0.08
    ournal
    -0.08
    ocache
    -0.08
     damn
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    ä½Ĩåį´
    -0.08
    POSITIVE LOGITS
    å°±æĺ¯è¿Ļæł·
    0.10
    è¿ĻèĪ¬
    0.09
    è¿Ļè¾¹
    0.08
    ç½ijé¦ĸ页
    0.08
    anca
    0.08
    LICENSE
    0.08
    ãģĵãģĵãģ¾ãģ§
    0.08
     ìĸ
    0.08
    âĢ¦I
    0.08
     Bris
    0.07
    Activations Density 2.170%

    No Known Activations