© 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. 2085
    Prev
    Next
    INDEX
    Explanations

    draft picks

    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
    éĺĻ
    -0.09
    å±±åºĦ
    -0.09
    æĶ»åĿļ
    -0.09
    å®ĺåħµ
    -0.09
    usher
    -0.09
    åħĭæľį
    -0.09
    ä¾¦å¯Ł
    -0.08
    ä¼ĺåĬ¿
    -0.08
    è¿Ļ两天
    -0.08
    terior
    -0.08
    POSITIVE LOGITS
    æ²Ļæ¼ł
    0.09
    è·³
    0.09
    _FN
    0.09
    Declared
    0.08
    çļĦ年轻人
    0.08
    eded
    0.08
    genesis
    0.08
    .son
    0.08
    åĨľåľº
    0.08
    åIJij社ä¼ļ
    0.08
    Activations Density 0.119%

    No Known Activations