© 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. 18687
    Prev
    Next
    INDEX
    Explanations

    Abe, San, anka

    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
    tty
    -0.09
    渤
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.08
     Fog
    -0.08
    ĺ认
    -0.08
    ledge
    -0.08
    ä¸įåĩº
    -0.08
    æļĸæ°Ķ
    -0.08
    åIJĪæ³ķæĢ§
    -0.08
    ancel
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.10
    ðŁı¼
    0.09
    æıī
    0.09
    èĬ·
    0.08
    rup
    0.08
    rew
    0.08
     volum
    0.08
    emu
    0.08
     Patel
    0.08
    fos
    0.08
    Activations Density 0.004%

    No Known Activations