© 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. 54247
    Prev
    Next
    INDEX
    Explanations

    WM media player

    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
    æĪıæĽ²
    -0.10
    åĹ½
    -0.10
    ä»Ģä¹Īåı«
    -0.09
    缱
    -0.09
    æĸ¯åŁº
    -0.09
    æİ¡åıĸ
    -0.09
     tháºŃp
    -0.09
    å¸ĮæľĽèĩªå·±
    -0.09
    棻
    -0.09
    åĪĨæľŁ
    -0.08
    POSITIVE LOGITS
    svp
    0.09
    éĢ¼
    0.09
    apur
    0.09
    ders
    0.08
    ains
    0.08
    çİĦ
    0.08
     Lamar
    0.08
    alen
    0.08
     SIN
    0.08
    eing
    0.08
    Activations Density 0.005%

    No Known Activations