© 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. 31127
    Prev
    Next
    INDEX
    Explanations

    onset of

    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
    /pol
    -0.09
    è¯Ĵ
    -0.09
    ç½ijç»ľä¼łæĴŃ
    -0.08
    宥
    -0.08
    æĶ¾è¿ĩ
    -0.08
     noqa
    -0.08
    ãĥ¼ãĥī
    -0.08
    .Release
    -0.08
    æ²¥
    -0.08
    æ»ĵ
    -0.08
    POSITIVE LOGITS
    /off
    0.10
    ein
    0.10
    eg
    0.09
    管å§Ķä¼ļ
    0.09
    bek
    0.09
    éĢŁåº¦å¿«
    0.09
    eous
    0.09
    tings
    0.09
    imes
    0.09
    ime
    0.09
    Activations Density 0.020%

    No Known Activations