© 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. 22614
    Prev
    Next
    INDEX
    Explanations

    FPGA

    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
    å¸ļ
    -0.08
    าย
    -0.08
    -0.07
    éĥİ
    -0.07
    pi
    -0.07
    è·ĥ
    -0.07
    èĭ±æīį
    -0.07
    3
    -0.07
    2
    -0.07
    1
    -0.07
    POSITIVE LOGITS
     rein
    0.11
    itized
    0.10
    è¿Ļåľº
    0.10
     MERCHANTABILITY
    0.10
    ç«£
    0.09
    å¾Ĺåĩº
    0.09
    ç½ijç«Ļåľ°åĽ¾
    0.09
    æ¢Ń
    0.09
    èŁ¾
    0.09
    ìķµ
    0.09
    Activations Density 0.089%

    No Known Activations