© 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. 58111
    Prev
    Next
    INDEX
    Explanations

    forever

    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
    åĽŀäºĭ
    -0.09
    lets
    -0.09
    ervo
    -0.09
    ively
    -0.08
    itude
    -0.08
    hek
    -0.08
    è´§è¿IJ
    -0.08
    sf
    -0.08
    room
    -0.08
    leton
    -0.08
    POSITIVE LOGITS
    hin
    0.11
    说æĺ¯
    0.10
    bidden
    0.09
    idan
    0.09
    ä¸įå¿ĺ
    0.09
    .toolbox
    0.09
    theless
    0.08
    YP
    0.08
    th
    0.08
    ather
    0.08
    Activations Density 0.007%

    No Known Activations