© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    HN questions

    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
    éĵ¨
    -0.09
    丰ç¡ķ
    -0.09
    æĿ¾å¼Ľ
    -0.08
    æħij
    -0.08
     Dial
    -0.08
     Pier
    -0.08
    rotch
    -0.08
    æµģä¼ł
    -0.08
    è°¿
    -0.08
     Bingo
    -0.08
    POSITIVE LOGITS
    aseline
    0.09
     unge
    0.09
    aldi
    0.09
    æ´»ä¸ĭåİ»
    0.09
    æĪijåıĪ
    0.09
    unix
    0.09
    榨
    0.09
    æĪijæĺ¯
    0.09
    ä¿¡ç®±
    0.09
    iden
    0.08
    Activations Density 0.012%

    No Known Activations