© 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. 31601
    Prev
    Next
    INDEX
    Explanations

    diagnostic tools, apparatus, methods, and tests

    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
    ä¹İ
    -0.10
    tern
    -0.09
    foy
    -0.09
    åĪļ好
    -0.08
    _SIDE
    -0.08
     camper
    -0.08
    коÑģ
    -0.08
    azar
    -0.08
    復
    -0.08
     Elegant
    -0.08
    POSITIVE LOGITS
    AndUpdate
    0.13
    .CodeAnalysis
    0.12
    æīĭ段
    0.10
    alent
    0.09
    å¢Ĵ
    0.09
    ä½ĵ系建设
    0.09
    Ļ¨
    0.09
    iele
    0.09
    matic
    0.09
    -tool
    0.09
    Activations Density 0.052%

    No Known Activations