© 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. 33294
    Prev
    Next
    INDEX
    Explanations

    and now, and then

    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
    etur
    -0.10
    åĢŁ
    -0.09
    å¼Ģæĭĵ
    -0.09
    arus
    -0.09
    纬
    -0.09
     Matthews
    -0.08
    ople
    -0.08
    iali
    -0.08
    æĸ°å¼Ģ
    -0.08
    /back
    -0.08
    POSITIVE LOGITS
    ä¸Ģç«Ļ
    0.09
    âĺ°
    0.08
    ä¸įå¾Ĺå·²
    0.08
    被åĬ¨
    0.08
    æĥħ绪
    0.08
    è½½
    0.08
    Ñģов
    0.08
    羣缸
    0.08
    broadcast
    0.08
    sch
    0.08
    Activations Density 0.019%

    No Known Activations