© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9970
    Prev
    Next
    INDEX
    Explanations

    publish after work

    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
    çĭĴ
    -0.10
    åĽ¡
    -0.10
     zaj
    -0.10
    èĻı
    -0.09
    ALSE
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    人æĢ§åĮĸ
    -0.09
    çĮ¢
    -0.09
    ç´łè´¨æķĻèĤ²
    -0.09
    æ¹ĸ人
    -0.09
    POSITIVE LOGITS
    åĸī
    0.11
    è¾Ĥ
    0.09
    okit
    0.08
    ä¼ı
    0.08
    LOUR
    0.08
    çİĭåĽ½
    0.08
    è´¢ç¨İ
    0.07
    (shift
    0.07
    uto
    0.07
     throat
    0.07
    Activations Density 0.035%

    No Known Activations