© 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. 53548
    Prev
    Next
    INDEX
    Explanations

    vs, sectomy, carbohydrate

    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
    åĪ»
    -0.10
    é»ĺ
    -0.09
    åºĸ
    -0.09
    cko
    -0.09
    peg
    -0.08
    æĸĻçIJĨ
    -0.08
    裸
    -0.08
    ä¸ĢæĬĬ
    -0.08
    è·º
    -0.08
    bery
    -0.08
    POSITIVE LOGITS
    山谷
    0.10
    èį·
    0.09
    æĥĬåı¹
    0.09
    ä»ĸæĺ¯
    0.09
    å®ŀå¹²
    0.08
    å°±è¡Į
    0.08
    (char
    0.08
    殿
    0.08
    ç½IJ
    0.08
    è¡Ģ液循çݯ
    0.08
    Activations Density 0.110%

    No Known Activations