© 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. 8537
    Prev
    Next
    INDEX
    Explanations

    select words or items

    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
    ischer
    -0.09
    åIJĮåѦ
    -0.08
     crossed
    -0.08
    éĺ¶æ¢¯
    -0.08
    æ®Ĭ
    -0.08
    _Internal
    -0.08
    isch
    -0.08
    .codes
    -0.08
    çīĪæĿĥå½Ĵ
    -0.08
    à¸Ľà¸¥à¸²à¸¢
    -0.07
    POSITIVE LOGITS
    GetObject
    0.10
    两ç§į
    0.09
    两类
    0.09
    è½»è½»åľ°
    0.09
    å®ŀè·µç»ıéªĮ
    0.09
    è¿Ļ两ç§į
    0.09
    举起
    0.09
    å·©åĽº
    0.09
    antes
    0.09
    åħ¥åĽŃ
    0.08
    Activations Density 0.073%

    No Known Activations