© 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. 55844
    Prev
    Next
    INDEX
    Explanations

    javascript development

    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
    amic
    -0.09
    oola
    -0.09
    chl
    -0.09
    istik
    -0.08
    ream
    -0.08
     кÑĤо
    -0.08
    LOC
    -0.08
    дов
    -0.08
    wick
    -0.08
    ãĥĽãĥ¼ãĥ«
    -0.08
    POSITIVE LOGITS
    обоÑĢоÑĤ
    0.11
     оÑģнове
    0.11
    è¦ģçŁ¥éģĵ
    0.11
    饱
    0.10
     него
    0.09
    åŁºç¡Ģä¸Ĭ
    0.09
    ÑģÑĭ
    0.09
    ä¸ĢæŶ
    0.08
    ä¿IJ
    0.08
    éļħ
    0.08
    Activations Density 0.070%

    No Known Activations