© 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. 11010
    Prev
    Next
    INDEX
    Explanations

    subscription and subscriber related terms

    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
    éħį
    -0.11
    åķ¬
    -0.10
    ä¸į说
    -0.10
     tslint
    -0.08
    ç¯Ĩ
    -0.08
    说åĩºæĿ¥
    -0.08
    datal
    -0.08
     иÑģÑĤ
    -0.08
    åŁ
    -0.08
    æľªç»ıæİĪæĿĥ
    -0.08
    POSITIVE LOGITS
    éĬ®
    0.09
    åı°ä¸Ĭ
    0.09
    _dual
    0.09
    馥
    0.09
    说æĺİ书
    0.09
    ç®Ń
    0.09
    å®ŀè´¨
    0.09
    礼æĭľ
    0.09
    essen
    0.08
    jis
    0.08
    Activations Density 0.006%

    No Known Activations