© 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. 51131
    Prev
    Next
    INDEX
    Explanations

    how things change or affect others

    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
    åĵį
    -0.10
    缸çķ¶
    -0.10
    缸å½ĵ
    -0.10
    ç¨ļ
    -0.09
    strument
    -0.09
     поÑĤомÑĥ
    -0.09
    èĢĹè´¹
    -0.09
    èĬ±è´¹
    -0.09
    è¿Ļæł·çļĦè¯Ŀ
    -0.09
    è½»æĿ¾
    -0.08
    POSITIVE LOGITS
     various
    0.10
    ä¸įæŃ»
    0.09
     ÑĢазлиÑĩнÑĭе
    0.09
     manifest
    0.09
     Various
    0.09
     different
    0.09
    ä¸įåħ¬å¹³
    0.09
    åIJĦç§į
    0.09
    éģĵçIJĨ
    0.09
    çİĭçĪ·
    0.08
    Activations Density 0.110%

    No Known Activations