© 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. 4878
    Prev
    Next
    INDEX
    Explanations

    named after

    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
    ัà¸Ķ
    -0.09
    ä»»æķĻ
    -0.09
    ankan
    -0.09
    afil
    -0.09
    ä¸ĢåIJij
    -0.09
     Mori
    -0.08
    AEA
    -0.08
    OME
    -0.08
    ç»Ħç»ĩå®ŀæĸ½
    -0.08
    æ´
    -0.08
    POSITIVE LOGITS
    çļĦåIJįåŃĹ
    0.11
    çļĦä¸Ģç§į
    0.10
    åIJĽ
    0.10
    è°IJ
    0.09
    åIJįåŃĹ
    0.09
     Gh
    0.08
    áĥĸ
    0.08
    æŁIJç§į
    0.08
     Od
    0.08
    ãģ¯ãģĺ
    0.08
    Activations Density 0.230%

    No Known Activations