© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52414
    Prev
    Next
    INDEX
    Explanations

    head of a group or organization

    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
    ÑĢенд
    -0.08
    æĮļ
    -0.08
    GetCurrent
    -0.08
    oron
    -0.08
    adin
    -0.08
    äu
    -0.08
    ç´¯
    -0.08
    妥åįı
    -0.07
    æĭĵ
    -0.07
    .activ
    -0.07
    POSITIVE LOGITS
    å¸ı
    0.11
    æİĮ
    0.10
    trag
    0.10
    尽头
    0.10
     helm
    0.10
     operation
    0.09
    æİĮæݧ
    0.09
    åıijåĬĽ
    0.09
    åĭº
    0.09
    _OPERATION
    0.09
    Activations Density 0.037%

    No Known Activations