© 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. 61176
    Prev
    Next
    INDEX
    Explanations

    what i want to do is

    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
    adle
    -0.09
    ä½łæĢİä¹Ī
    -0.09
    vor
    -0.08
     bá»ı
    -0.08
    /is
    -0.08
    anine
    -0.08
    èµĸ以
    -0.08
    ä»Ģä¹ĪæĦıæĢĿ
    -0.08
    æĢİä¹ĪåĽŀäºĭ
    -0.08
    åĶ¯ä¸Ģ
    -0.08
    POSITIVE LOGITS
    çļĦæĺ¯
    0.16
     adalah
    0.13
    æĺ¯åľ¨
    0.13
    ãģ¯
    0.13
    便æĺ¯
    0.12
    æĺ¯
    0.12
    åĪĻæĺ¯
    0.11
    æĺ¯æ²¡æľī
    0.11
     is
    0.11
    å°±æĺ¯
    0.11
    Activations Density 0.270%

    No Known Activations