© 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. 17521
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    åģļåĪ°äºĨ
    -0.10
    èĭ±æł¼
    -0.09
    èĬľ
    -0.09
     Guinness
    -0.09
    è®·
    -0.09
    ä¸¤å¼ł
    -0.09
    èħĶ
    -0.09
    ä»ħä¾Ľ
    -0.08
    èĤ¢
    -0.08
    _reporting
    -0.08
    POSITIVE LOGITS
    tober
    0.09
    çŀ©
    0.08
    æ´Ĺ礼
    0.08
    ç»ĩ
    0.08
     Rice
    0.08
    à¸ģระà¸Ĺ
    0.08
    ä¸ĭä¸Ģ个
    0.07
    åĽŀ头
    0.07
    ä¸ºæľŁ
    0.07
    åĨ³æĪĺ
    0.07
    Activations Density 0.708%

    No Known Activations