© 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. 56981
    Prev
    Next
    INDEX
    Explanations

    coffee rust ale filter machine

    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
    çİĦ
    -0.09
    çĦī
    -0.09
     GPLv
    -0.09
    毫
    -0.09
    æīĵå¾Ĺ
    -0.09
     ÑĢеж
    -0.08
    inoa
    -0.08
    æīĵ好
    -0.08
    åŃķ
    -0.08
    åĬłçĽŁåºĹ
    -0.08
    POSITIVE LOGITS
    æŀľ
    0.11
    ç§ĭ
    0.10
    åIJ¬è¯Ŀ
    0.09
    åħ¨å¹´
    0.08
    çļĦæĢ§æł¼
    0.08
    ÑģпоÑģоб
    0.08
    åĬ¨çī©åĽŃ
    0.08
    对她
    0.08
    çħ§
    0.08
    _verts
    0.08
    Activations Density 0.021%

    No Known Activations