© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21267
    Prev
    Next
    INDEX
    Explanations

    turn to

    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
    mj
    -0.10
    é¾Ī
    -0.09
    诣
    -0.08
    èĩªåıij
    -0.08
    æľĽ
    -0.08
    orrent
    -0.08
    /utility
    -0.08
    éĥģ
    -0.08
    é«ĺä½İ
    -0.07
    åIJ¬å®Į
    -0.07
    POSITIVE LOGITS
    etti
    0.10
    _EXISTS
    0.10
    EIF
    0.10
    NX
    0.09
    isen
    0.09
    对è¯Ŀ
    0.09
     ÑĢеж
    0.09
    åªļ
    0.09
    çı£
    0.09
    antu
    0.09
    Activations Density 0.037%

    No Known Activations