© 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. 62491
    Prev
    Next
    INDEX
    Explanations

    series

    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
    篦
    -0.09
    顺
    -0.09
    座
    -0.09
    æĺİæĹ¥
    -0.09
     viv
    -0.08
     bib
    -0.08
     bod
    -0.08
    AMB
    -0.08
     geç
    -0.08
    heap
    -0.08
    POSITIVE LOGITS
    ç³»åĪĹ
    0.25
     series
    0.24
    ãĤ·ãĥªãĥ¼ãĤº
    0.21
    series
    0.20
    Series
    0.18
     Series
    0.18
    .series
    0.18
     SERIES
    0.17
    ç³»åĪĹ产åĵģ
    0.17
     ÑģеÑĢии
    0.17
    Activations Density 0.146%

    No Known Activations