© 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. 62275
    Prev
    Next
    INDEX
    Explanations

    namely

    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
    æŃ¹
    -0.09
    æĸ°æīĭ
    -0.09
     Cand
    -0.09
    aris
    -0.09
    ç¨Ĺ
    -0.09
    .Misc
    -0.09
    èĢĨ
    -0.09
    æķħäºĭ
    -0.09
    -parse
    -0.09
    å¥ĩ
    -0.09
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.11
     namely
    0.10
    lei
    0.09
    reh
    0.09
    羣æŃ£çļĦ
    0.09
    åºĶ该æĢİä¹Ī
    0.09
    éĤ£å°±æĺ¯
    0.09
    nam
    0.09
    reo
    0.09
    omet
    0.09
    Activations Density 0.103%

    No Known Activations