© 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. 49105
    Prev
    Next
    INDEX
    Explanations

    Stone Cherry, Tom Bell, Blue Bell

    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
    utors
    -0.10
    ient
    -0.10
    bsub
    -0.09
    ĪæĿĥ
    -0.09
    stants
    -0.09
    hamster
    -0.09
    obody
    -0.09
    æĬĬæīĭ
    -0.09
    iture
    -0.09
    ðŁĵ£
    -0.09
    POSITIVE LOGITS
    è¯ļæĦı
    0.10
    ç»İ
    0.09
    edly
    0.09
    /black
    0.09
    缮
    0.08
    æµĵ
    0.08
    大家éĥ½åľ¨
    0.08
    ning
    0.08
    pe
    0.08
    ä»İ严治
    0.08
    Activations Density 0.063%

    No Known Activations