© 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. 27806
    Prev
    Next
    INDEX
    Explanations

    small amounts

    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
    空åīį
    -0.10
    edImage
    -0.10
    /from
    -0.10
    edio
    -0.10
    家人
    -0.09
    æŀģ度
    -0.09
    atre
    -0.09
    å¥Ĥ
    -0.09
    edes
    -0.09
    èīºäºº
    -0.08
    POSITIVE LOGITS
    æĻĤåĢĻ
    0.10
    elm
    0.10
    /tiny
    0.09
    åŀĽ
    0.09
    /small
    0.09
    å²Ĺ
    0.09
    gro
    0.09
    енÑĮ
    0.09
    身åŃIJ
    0.09
    ä¸įå°ı
    0.08
    Activations Density 0.003%

    No Known Activations