© 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. 34203
    Prev
    Next
    INDEX
    Explanations

    connecting concepts

    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
    ÙħÙĬØ©
    -0.09
    olini
    -0.09
    ç¢Ľ
    -0.09
     cracks
    -0.09
    olin
    -0.09
    åı³æīĭ
    -0.09
    å°ıèħ¿
    -0.08
    enza
    -0.08
    æ¶ķ
    -0.08
    apan
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶
    0.13
    çī¹åĪ«æĺ¯
    0.10
    ä¸İåħ¶
    0.10
    åıĬ缸åħ³
    0.09
    ä¸įåı¯ä»¥
    0.09
    åħ¶å®ĥ
    0.09
    åħ¶ä»ĸçļĦ
    0.09
     other
    0.09
    以åħ¶
    0.09
     дÑĢÑĥгими
    0.09
    Activations Density 0.544%

    No Known Activations