© 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. 33982
    Prev
    Next
    INDEX
    Explanations

    steroid

    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
    åłŀ
    -0.10
     долж
    -0.09
    ï¸
    -0.09
    IsUnicode
    -0.09
    åī¯ä¼ļéķ¿
    -0.09
    è¿ijäºĽ
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    ä¸įæĸŃçļĦ
    -0.09
    ç±³ç²ī
    -0.09
    æĸ°æĿIJæĸĻ
    -0.09
    POSITIVE LOGITS
     harness
    0.08
    è¾ķ
    0.08
    è¾
    0.08
    éŀ
    0.07
    åĸĩ
    0.07
    æĶĴ
    0.07
    вл
    0.07
     bullet
    0.07
    æľīä¸Ģä½į
    0.07
     ÙĦدÙĬÙĨا
    0.07
    Activations Density 0.692%

    No Known Activations