© 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. 38702
    Prev
    Next
    INDEX
    Explanations

    date, chronograph, time, modes, Speedmaster

    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
    ä¸ŃåİŁ
    -0.10
    ride
    -0.09
     tow
    -0.09
    èĪĮ头
    -0.09
    åŃĹåı·
    -0.09
    æ¯Ķäºļ
    -0.09
    .ke
    -0.09
    æĸ¹æīį
    -0.08
    æµĵæµĵçļĦ
    -0.08
    usty
    -0.08
    POSITIVE LOGITS
    å¤į
    0.10
    åľŃ
    0.10
    avra
    0.09
    arris
    0.09
    _disabled
    0.09
    ä¸Ĭå¹´
    0.09
    ä¸ĢåIJ¬
    0.08
    éĨĴ缮
    0.08
     Clair
    0.08
    ä¸Ģ人
    0.08
    Activations Density 0.113%

    No Known Activations