© 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. 23415
    Prev
    Next
    INDEX
    Explanations

    arrested

    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
    ldr
    -0.10
    èµ°ä¸ĭåİ»
    -0.10
    DAL
    -0.10
    Terr
    -0.10
    èѦåĬ¡
    -0.09
    äl
    -0.09
    би
    -0.09
     ÑģÑĤÑĥд
    -0.09
    æ¯ıä¸Ģ个人
    -0.09
     Damon
    -0.09
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.09
    天æīį
    0.09
    rica
    0.09
    ÑĪин
    0.09
    ä¸īä½įä¸Ģä½ĵ
    0.08
     ho
    0.08
    å°±æĺ¯åĽłä¸º
    0.08
    _REQUIRE
    0.08
    tas
    0.08
    举
    0.08
    Activations Density 0.056%

    No Known Activations