© 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. 39396
    Prev
    Next
    INDEX
    Explanations

    I need

    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
    æĪijçŁ¥éģĵ
    -0.11
    åľ°æ®µ
    -0.10
    çĬĴ
    -0.09
    åħļå§Ķ书记
    -0.09
    æİł
    -0.09
    é©Ń
    -0.09
    å·¢
    -0.09
    åľŁè±ª
    -0.09
    åIJĥä»Ģä¹Ī
    -0.09
    ฤ
    -0.09
    POSITIVE LOGITS
    åĭ¾
    0.09
    gon
    0.09
    _basename
    0.09
    åĸľçĪ±
    0.08
     gon
    0.08
    éĿ¢ä¸´çļĦ
    0.08
    habi
    0.08
    esda
    0.07
    ä¸įå¾Ĺä¸į
    0.07
    ãģŁãģ¡
    0.07
    Activations Density 0.521%

    No Known Activations