© 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. 35145
    Prev
    Next
    INDEX
    Explanations

    section headings

    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
    åĩĨ
    -0.09
    থ
    -0.08
    omic
    -0.08
    ingly
    -0.08
    ä¸ĩåįļ
    -0.08
     Ear
    -0.08
     Tango
    -0.07
    jang
    -0.07
    å¾Ĺä½ı
    -0.07
    ally
    -0.07
    POSITIVE LOGITS
    çĻ¾ç§ij
    0.11
    æİ¥æīĭ
    0.09
    ä¸įæ¸ħ
    0.09
    ä¸ºè¿Ľä¸ĢæŃ¥
    0.09
    人éĥ½
    0.09
    æĹłç©·
    0.09
    ä¸Ģå¼Ģå§ĭå°±
    0.09
    ATOM
    0.09
    odore
    0.09
    æľĭåıĭ们
    0.09
    Activations Density 0.563%

    No Known Activations