© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50708
    Prev
    Next
    INDEX
    Explanations

    from

    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
    аÑĤÑĥÑĢ
    -0.10
    å¼Ħ
    -0.09
    éĴµ
    -0.09
    ç¬ı
    -0.09
    éķı
    -0.08
    agram
    -0.08
    è¿ĻèĪ¬
    -0.08
    æĺİçıł
    -0.08
    .bz
    -0.08
    ãģ³
    -0.08
    POSITIVE LOGITS
    åĬłå¤§
    0.10
    åIJĦ个æĸ¹éĿ¢
    0.10
    éĺ²çĽĹ
    0.09
    æĹģ
    0.09
    çľĭçĿĢ
    0.09
    åĩºåıij
    0.09
    èµ°å»Ĭ
    0.09
    åĬ¨çĶŁæĪIJ
    0.09
    æ§IJ
    0.09
    ereg
    0.09
    Activations Density 0.105%

    No Known Activations