© 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. 34043
    Prev
    Next
    INDEX
    Explanations

    ultrasound diagnostic investigation

    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
    çĦ¶æĺ¯
    -0.11
    ness
    -0.10
    yard
    -0.10
    ÑĤÑı
    -0.10
    iment
    -0.10
    ney
    -0.09
    acity
    -0.09
    æ°ĹãģĮ
    -0.08
    è¿IJåĬ¨ä¼ļ
    -0.08
    inary
    -0.08
    POSITIVE LOGITS
    sing
    0.12
    ðŁı»
    0.10
    ðŁı¼
    0.10
    achusetts
    0.10
    ç«Ļéķ¿
    0.09
    able
    0.09
    çĺģ
    0.09
    _rng
    0.09
    otten
    0.09
    ±
    0.08
    Activations Density 0.003%

    No Known Activations