© 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. 32966
    Prev
    Next
    INDEX
    Explanations

    assume that

    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
    æĪijè§īå¾Ĺ
    -0.09
    dbo
    -0.08
    è¿Ŀåıį
    -0.08
    plete
    -0.08
    åı¯ä»¥è¯´æĺ¯
    -0.08
     пов
    -0.08
    obb
    -0.08
    å¾Ģå¾Ģ
    -0.08
     reportedly
    -0.08
    æį¢
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļæĪĸå°ij
    0.10
    好äºĨ
    0.10
    åIJĪçIJĨæĢ§
    0.09
    é¢ĺ主
    0.09
    åIJĪçIJĨ
    0.09
    æľĢåŁºæľ¬
    0.09
    年代
    0.09
    .getAs
    0.09
    è¶³å¤Ł
    0.09
    orno
    0.08
    Activations Density 0.077%

    No Known Activations