© 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. 51268
    Prev
    Next
    INDEX
    Explanations

    precipitation and inches

    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
     legion
    -0.09
     assignable
    -0.08
    URN
    -0.08
     Lancaster
    -0.08
    .writ
    -0.08
    æľīæĦıæĢĿ
    -0.08
    è·¯åı£
    -0.08
    èĸª
    -0.08
     Burning
    -0.08
    éĢĨ
    -0.08
    POSITIVE LOGITS
    累积
    0.11
    aul
    0.10
    累计
    0.09
    æ³»
    0.09
    icer
    0.09
    åİļåİļçļĦ
    0.09
    éľ
    0.09
    æĢ»éĩı
    0.08
    åıĹçģ¾
    0.08
    足
    0.08
    Activations Density 0.021%

    No Known Activations