© 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. 33266
    Prev
    Next
    INDEX
    Explanations

    email communication

    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
    TRS
    -0.10
    etter
    -0.09
    notated
    -0.09
    ate
    -0.09
    ometry
    -0.09
    olut
    -0.09
    abbage
    -0.08
    å±ĭåŃIJ
    -0.08
     Airways
    -0.08
    arter
    -0.08
    POSITIVE LOGITS
    chimp
    0.11
    ä¸Ģå°ģ
    0.10
    /email
    0.10
    å·¥åİĤ
    0.09
    antine
    0.09
    ä¸įéĢļ
    0.09
    ç¼Ń
    0.09
    tı
    0.09
    aly
    0.08
    PILE
    0.08
    Activations Density 0.037%

    No Known Activations