© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    memory allocation exceptions

    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
    elves
    -0.11
    ãģĹãģ¾ãģĨ
    -0.10
    lessly
    -0.10
    like
    -0.10
    akit
    -0.10
    ful
    -0.09
    folk
    -0.09
    cape
    -0.09
    tracks
    -0.09
    orary
    -0.09
    POSITIVE LOGITS
    ä¸ĭæĿ¥çļĦ
    0.10
    æĢ¯
    0.10
    ij
    0.09
    塾
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    leh
    0.09
    éļ¾æĢª
    0.09
    lect
    0.09
    ally
    0.09
    lement
    0.09
    Activations Density 0.023%

    No Known Activations