© 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. 58515
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements

    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
    ocracy
    -0.11
    /operators
    -0.10
     Trom
    -0.10
    onom
    -0.09
    ÙĪار
    -0.09
    vie
    -0.09
    ê¹IJ
    -0.08
    ãĥ©ãĥ³ãĥī
    -0.08
    ÑģоÑĢ
    -0.08
    è¾£
    -0.08
    POSITIVE LOGITS
    å¾ģæ±Ĥ
    0.09
    æĶ¶èİ·
    0.09
    æĺı
    0.09
    æ³±
    0.09
    æij§
    0.09
    çļĦèĢģ
    0.08
    é¾Ħ
    0.08
    çĦ¯
    0.08
    åĽ¾çīĩæĿ¥æºIJ
    0.08
    æĢ»çļĦæĿ¥è¯´
    0.08
    Activations Density 0.002%

    No Known Activations