© 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. 63665
    Prev
    Next
    INDEX
    Explanations

    known by everyone

    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
    çĶ¨éĩı
    -0.09
     reun
    -0.09
     zob
    -0.09
    èµĦè´¨
    -0.08
    åĨ²åĬ¨
    -0.08
     ÐIJвÑĤоÑĢ
    -0.08
    æŁĦ
    -0.08
    çīĪæĿĥ
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    полн
    -0.08
    POSITIVE LOGITS
    çŁ¥æĻĵ
    0.14
    æĤī
    0.13
    çļĦåIJįåŃĹ
    0.11
    ä¸ĩæĪ·
    0.11
    åĽ½åĨħå¤ĸ
    0.10
    è¿Ļ个åIJįåŃĹ
    0.10
    家åĸ»æĪ·æĻĵ
    0.10
    ilot
    0.10
    并ä¸įæĺ¯å¾Ī
    0.10
    å§ĵåIJį
    0.10
    Activations Density 0.058%

    No Known Activations