© 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. 58642
    Prev
    Next
    INDEX
    Explanations

    easy to use

    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
    讲课
    -0.10
    éģĹ
    -0.09
    è§Ī
    -0.09
    ä¸Ģä½ĵåĮĸ
    -0.09
    _USAGE
    -0.09
    usage
    -0.09
     Alexandre
    -0.09
    大大å°ıå°ı
    -0.08
    åħ¸åŀĭçļĦ
    -0.08
    USAGE
    -0.08
    POSITIVE LOGITS
    ertools
    0.10
    åıĭ好
    0.10
    åı°ä¸Ĭ
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    Friendly
    0.08
    -friendly
    0.08
    æĬĬä½ł
    0.08
    ango
    0.08
    itty
    0.08
     Roc
    0.08
    Activations Density 0.014%

    No Known Activations