© 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. 18801
    Prev
    Next
    INDEX
    Explanations

    stumble upon/across

    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
    rase
    -0.09
    edm
    -0.09
    ä¸įæĿ¥
    -0.08
    arf
    -0.08
    头èĦij
    -0.08
    achs
    -0.08
    Lik
    -0.08
    MED
    -0.07
    ither
    -0.07
    çļĦç¡®
    -0.07
    POSITIVE LOGITS
    ç»Ĭ
    0.10
    æŃ¥ä¼IJ
    0.09
    èĤ¥
    0.09
    çłĮ
    0.09
    imentary
    0.09
    模仿
    0.09
    è¸ī
    0.09
    .syntax
    0.08
    éŀĭ
    0.08
    åIJijåīį
    0.08
    Activations Density 0.012%

    No Known Activations