© 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. 61149
    Prev
    Next
    INDEX
    Explanations

    snout or nose

    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
    ehler
    -0.10
    çĸĿ
    -0.09
    моÑĤ
    -0.09
     createState
    -0.08
    erner
    -0.08
     dealloc
    -0.08
    å·©
    -0.08
    妾
    -0.08
    é©¿ç«Ļ
    -0.08
     Bates
    -0.08
    POSITIVE LOGITS
     SAR
    0.10
    é¼»åŃIJ
    0.10
    çĵľ
    0.10
    åĺ´
    0.09
    æĤ¯
    0.09
     noses
    0.09
     nose
    0.09
    欣æħ°
    0.09
    许åı¯è¯ģ
    0.09
    éĵĽ
    0.09
    Activations Density 0.075%

    No Known Activations