© 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. 27389
    Prev
    Next
    INDEX
    Explanations

    word tracking, fluency, spellings

    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
     ver
    -0.09
    udent
    -0.09
    umann
    -0.08
    åģ¥åº·äº§ä¸ļ
    -0.08
    é¼İ
    -0.08
     Äijóng
    -0.08
    Plans
    -0.08
    arent
    -0.08
    è´«
    -0.08
    åī§ä¸Ń
    -0.08
    POSITIVE LOGITS
    phon
    0.10
    .readString
    0.10
    è¯Ĩ
    0.10
    glyph
    0.09
     Phon
    0.09
    æĭ¼éŁ³
    0.09
    æīĴ
    0.09
    æĭİ
    0.09
    读
    0.09
    .decrypt
    0.09
    Activations Density 0.033%

    No Known Activations