© 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. 53958
    Prev
    Next
    INDEX
    Explanations

    volume ofemails

    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
    UNCT
    -0.10
    åħ¨å¥Ĺ
    -0.10
    精度
    -0.10
    marshall
    -0.09
    /LICENSE
    -0.09
    è¾Ľè¾£
    -0.09
    éĤ»å±ħ
    -0.09
    çŁ¥æĥħ
    -0.09
    untime
    -0.09
    éĤ»
    -0.09
    POSITIVE LOGITS
    æĶ¶åĪ°
    0.13
     incoming
    0.11
    æ¯ı天
    0.11
    æĿ¥çĶµ
    0.11
    åIJĦç§įåIJĦæł·
    0.10
    æİ¥åĪ°
    0.10
     requests
    0.10
    æĿ¥è®¿
    0.10
    åıĹçIJĨ
    0.10
    æ¶Įåħ¥
    0.10
    Activations Density 0.076%

    No Known Activations