© 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. 58763
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

    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
    车éģĵ
    -0.09
    对å¾ħ
    -0.09
    chen
    -0.08
    èį£
    -0.08
    gon
    -0.08
    å¼ĤæĢ§
    -0.08
    paralle
    -0.08
    è¥Ħ
    -0.08
    个åĪ«
    -0.08
    å¯Ł
    -0.08
    POSITIVE LOGITS
    oya
    0.09
    ç¼Ľ
    0.09
    çĤ¬
    0.09
    æĪĺçģ«
    0.09
    erture
    0.09
    ofire
    0.09
    _tar
    0.09
    缸åħ³è§Ħå®ļ
    0.08
    _CUDA
    0.08
    涵
    0.08
    Activations Density 0.002%

    No Known Activations