© 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. 11979
    Prev
    Next
    INDEX
    Explanations

    CMOS, MOSFET, implant, oxide, device structures

    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
    æIJº
    -0.09
    衾
    -0.09
    æ½¢
    -0.09
    åįĩ
    -0.09
    åı¤ä»Ĭ
    -0.09
    ç³Ļ
    -0.08
    _PROVID
    -0.08
    天èĬ±æĿ¿
    -0.08
    ä¸įåħ·å¤ĩ
    -0.08
    ToOne
    -0.08
    POSITIVE LOGITS
    èĵĦ
    0.10
    庶
    0.09
    stance
    0.09
    禹
    0.09
    keh
    0.09
    产ä¸ļåŁºåľ°
    0.09
    rael
    0.09
    -base
    0.09
    hood
    0.08
    èĤ¡æ°ij
    0.08
    Activations Density 0.294%

    No Known Activations