© 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. 55713
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¹Łä¸įä¼ļ
    -0.10
    áng
    -0.09
    åĩī
    -0.09
    æĢ§å¼º
    -0.09
    Ru
    -0.08
    è¡ħ
    -0.08
    èī¯
    -0.08
    è°ĥæŁ¥æĺ¾ç¤º
    -0.08
    诸èijĽ
    -0.08
    ings
    -0.08
    POSITIVE LOGITS
    ish
    0.11
    åĭĥ
    0.09
    _closure
    0.09
    带ä¸Ĭ
    0.09
    è¹ĭ
    0.09
    OPS
    0.09
    æīĭæ³ķ
    0.08
    otime
    0.08
    emu
    0.08
    ISH
    0.08
    Activations Density 0.180%

    No Known Activations