© 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. 61970
    Prev
    Next
    INDEX
    Explanations

    rhythm

    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
    orate
    -0.09
    imir
    -0.09
    æĻ°
    -0.09
    ạnh
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    ye
    -0.08
    å³¥
    -0.08
     Modelo
    -0.08
    åĽ½åĬ¡
    -0.08
    imon
    -0.08
    POSITIVE LOGITS
    èĬĤå¥ı
    0.13
    åįģ足
    0.11
    æİĮæı¡äºĨ
    0.11
     rhythm
    0.09
    æ°ijå¿ĥ
    0.09
    еÑĢж
    0.09
    ONSE
    0.09
     stride
    0.08
    åįĬå²Ľ
    0.08
    èµ°åľ¨
    0.08
    Activations Density 0.019%

    No Known Activations