© 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. 17491
    Prev
    Next
    INDEX
    Explanations

    winning streaks and losses

    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
    åħ¨ç¨ĭ
    -0.12
    ä¸Ģè¾ĪåŃIJ
    -0.11
    æĺİå¹´
    -0.11
    ä¸ĭåįĬå¹´
    -0.11
    ç»Ī身
    -0.10
    åħ¨å¹´
    -0.10
    è¿Ļè¾ĪåŃIJ
    -0.10
    贯穿
    -0.10
    åIJĦåĽ½
    -0.10
    è¿Ļä¸Ģå¹´
    -0.09
    POSITIVE LOGITS
    å¾®éĩı
    0.11
    inky
    0.09
    ارد
    0.08
    éĺ´
    0.08
    ä¸Ķ
    0.08
    çĥľ
    0.08
    íĸī
    0.08
    irk
    0.08
     th
    0.08
    ä¸ĵ人
    0.08
    Activations Density 0.036%

    No Known Activations