© 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. 53699
    Prev
    Next
    INDEX
    Explanations

    to not want

    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
    _AUX
    -0.10
    asher
    -0.09
    è¾ŀ
    -0.09
    ırım
    -0.09
     Giles
    -0.09
    å¯Ĥ
    -0.09
    UsageId
    -0.09
    è¾Ń
    -0.08
    enas
    -0.08
    æĤ¬
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
    cert
    0.11
    ä¹Łä¸įæĥ³
    0.10
     cert
    0.10
    夺åıĸ
    0.10
    éĴĩ
    0.10
    CERT
    0.09
    pm
    0.09
    太快
    0.09
     unless
    0.09
    Activations Density 0.037%

    No Known Activations