© 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. 63037
    Prev
    Next
    INDEX
    Explanations

    bulk purchase or order

    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
     Bard
    -0.11
    çĻ¾åĪĨçĻ¾
    -0.09
    FAILED
    -0.08
    åĻ¨
    -0.08
    snippet
    -0.08
    _bs
    -0.08
    ogn
    -0.08
    orest
    -0.08
    ä¸Ģ头
    -0.08
    ä¹±
    -0.08
    POSITIVE LOGITS
    bulk
    0.13
    æī¹éĩı
    0.13
     bulk
    0.13
    Bulk
    0.11
     Bulk
    0.11
    ä¸į满
    0.10
    æ³Ķ
    0.10
     ÑĢаÑģпÑĢоÑģÑĤ
    0.10
    è¿ĩ硬
    0.10
    念
    0.10
    Activations Density 0.034%

    No Known Activations