© 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. 62625
    Prev
    Next
    INDEX
    Explanations

    used as, or used in

    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
    _malloc
    -0.09
    对åħ¶è¿Ľè¡Į
    -0.08
    浪潮
    -0.08
     mistress
    -0.08
    æĪijè¦ģ
    -0.08
    .Typed
    -0.08
    contri
    -0.08
    fabs
    -0.08
    APE
    -0.08
    .Iter
    -0.07
    POSITIVE LOGITS
    å½ĵä½ľ
    0.15
    å½ĵåģļ
    0.14
    å½ĵæĪIJ
    0.13
    ä½ľä¸º
    0.12
    å½ĵå±Ģ
    0.12
    ä¹Łåı¯
    0.11
    ä½ľä¸ºä¸Ģç§į
    0.11
    ä»£æĽ¿
    0.10
    ä¹Łåı¯ä»¥
    0.10
    ä½ľçĤº
    0.10
    Activations Density 0.085%

    No Known Activations