© 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. 55893
    Prev
    Next
    INDEX
    Explanations

    month day

    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
    äººåľ¨
    -0.09
    è¿ĺåİŁ
    -0.09
    äºİæĺ¯
    -0.08
    erer
    -0.08
    ä»İæĿ¥
    -0.08
    泡
    -0.08
    责任åĪ¶
    -0.08
    ä¾ĽçĥŃ
    -0.08
    paces
    -0.07
    pec
    -0.07
    POSITIVE LOGITS
    æĹ¥åľ¨
    0.11
    æĿ¥ä¸´
    0.10
    ä¹Łä¸įè¦ģ
    0.09
    _DEN
    0.09
    aben
    0.09
    DAY
    0.09
    ale
    0.09
    çªģå¦Ĥåħ¶æĿ¥
    0.08
    Æ°ng
    0.08
    dle
    0.08
    Activations Density 0.038%

    No Known Activations