© 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. 34580
    Prev
    Next
    INDEX
    Explanations

    impact or affect

    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
    è¶³å¤Ł
    -0.10
     Reviewed
    -0.09
    CHK
    -0.09
    æĶ»åĬ¿
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
    å¹ķ
    -0.08
    ersen
    -0.08
     Ñıв
    -0.08
    ows
    -0.08
    .nlm
    -0.08
    POSITIVE LOGITS
     overall
    0.10
     whether
    0.10
    æķ´ä¸ªäºº
    0.10
    è¦ģä¸įè¦ģ
    0.10
    以ä¸ĭåĩłä¸ª
    0.10
     how
    0.09
    èĥ½åIJ¦
    0.09
    社ä¼ļ稳å®ļ
    0.09
    å¾Īå¤ļäºĭæĥħ
    0.09
    åĩĨ
    0.09
    Activations Density 0.123%

    No Known Activations