© 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. 17958
    Prev
    Next
    INDEX
    Explanations

    bands and music releases

    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
    ä¸įåĪĨ
    -0.09
    踵
    -0.09
    鸮
    -0.09
    zew
    -0.09
    个人è§ĤçĤ¹
    -0.09
    ä¸įæĪIJ
    -0.09
    è§IJ
    -0.09
    orgh
    -0.09
    Ãłng
    -0.09
    _reserved
    -0.08
    POSITIVE LOGITS
    åħĪ导
    0.09
    æłĵ
    0.09
    ãĥģãĥ¥
    0.09
    æĬĬèĩªå·±çļĦ
    0.08
    .cli
    0.08
    ffield
    0.08
    кÑĢаÑĤ
    0.08
    iral
    0.08
    æĭ´
    0.08
    .setError
    0.08
    Activations Density 0.102%

    No Known Activations