© 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. 17200
    Prev
    Next
    INDEX
    Explanations

    considering assumptions

    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
    çĽİ
    -0.09
    åĬ¡
    -0.09
    isz
    -0.09
    лей
    -0.09
    ç°§
    -0.08
    ãĤ·ãĥª
    -0.08
    渡
    -0.08
     ÑģлÑĥж
    -0.08
    _sol
    -0.08
     embarrass
    -0.08
    POSITIVE LOGITS
    çŃīåĽłç´ł
    0.11
    åģĩ设
    0.10
     realistically
    0.10
     Perfect
    0.10
    è¾ĥ强çļĦ
    0.10
    æģĴ
    0.10
    çļĦåĽłç´ł
    0.10
     hypoth
    0.09
    perfect
    0.09
    æĬĢæľ¯æ°´å¹³
    0.09
    Activations Density 0.356%

    No Known Activations