© 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. 11871
    Prev
    Next
    INDEX
    Explanations

    python scripts

    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
    轸
    -0.09
    gMaps
    -0.09
    à¹Ĥà¸Ľà¸£à¹ģ
    -0.09
    ï¹Ģ
    -0.08
    _rsa
    -0.08
    KANJI
    -0.08
    çľ¼çļ®
    -0.08
    GMEM
    -0.08
    ðŁĵĨ
    -0.08
    ÙħÙĨتدÙĬات
    -0.08
    POSITIVE LOGITS
    ally
    0.08
    éĴī
    0.08
    fully
    0.08
    ses
    0.07
    emb
    0.07
    la
    0.07
    åĩłä½į
    0.07
    lah
    0.07
    åIJĦç±»
    0.07
    æIJĵ
    0.07
    Activations Density 0.782%

    No Known Activations