© 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. 47820
    Prev
    Next
    INDEX
    Explanations

    taking advantage of

    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
    ä¸įå®ļ
    -0.11
    trs
    -0.11
    ãģªãĤĭ
    -0.10
    à§į
    -0.10
    angent
    -0.10
    åĬ£
    -0.09
    ä¿ĺ
    -0.09
    PIP
    -0.09
    icycle
    -0.09
    ứ
    -0.09
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.09
    abilities
    0.08
    主èIJ¥
    0.08
    лÑıем
    0.08
    æİĸ
    0.08
    åIJŃ
    0.08
     keen
    0.08
    ÙĦس
    0.08
    .Builder
    0.08
    (rep
    0.07
    Activations Density 0.003%

    No Known Activations