© 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. 23492
    Prev
    Next
    INDEX
    Explanations

    political party leaders

    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
    Bright
    -0.10
    ç¤ģ
    -0.10
    æ¡Įä¸Ĭ
    -0.09
    åĸŁ
    -0.09
    uter
    -0.09
    è¯ŀ
    -0.09
    羣缸
    -0.08
    FI
    -0.08
    æĤ¼
    -0.08
    Pred
    -0.08
    POSITIVE LOGITS
    ections
    0.08
    åĪĽå§ĭ人
    0.08
    bett
    0.08
    bul
    0.08
    VALID
    0.08
    ä¸Ģæĸ¹
    0.08
    派人
    0.08
    æijĨ
    0.08
    对èĩªå·±
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    Activations Density 0.024%

    No Known Activations