© 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. 10690
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    isz
    -0.10
    onet
    -0.10
    oyal
    -0.10
    个çĻ¾åĪĨ
    -0.10
    æĮĿ
    -0.10
    pson
    -0.10
     Testament
    -0.09
    责任åĪ¶
    -0.09
    ðŁı»
    -0.09
    åĬ¨çĶŁæĪIJ
    -0.09
    POSITIVE LOGITS
    urator
    0.09
    richt
    0.09
    rale
    0.09
    éģIJ
    0.09
    edly
    0.09
    ÑĢоÑģ
    0.08
     ìķĬëĬĶ
    0.08
    arian
    0.08
    éĤ³
    0.08
    iosk
    0.08
    Activations Density 0.204%

    No Known Activations