© 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. 53997
    Prev
    Next
    INDEX
    Explanations

    avian neurologic syndrome

    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
    lov
    -0.09
    è¯Ĭ
    -0.09
    æĤ±
    -0.09
    åĪĺæµ·
    -0.08
    leys
    -0.08
    æĬ¥éħ¬
    -0.08
    浴室
    -0.08
    åĹŁ
    -0.08
    çļĦ女人
    -0.08
     trou
    -0.08
    POSITIVE LOGITS
    å¸Ń
    0.11
    èµ·é£ŀ
    0.10
    鸥
    0.10
     zab
    0.09
    çĤİ
    0.09
    åĽŀ头
    0.09
    ä¸įæİĴéĻ¤
    0.09
    [at
    0.09
    ä¸ĥæĺŁ
    0.09
     Overse
    0.09
    Activations Density 0.107%

    No Known Activations