© 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. 33933
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    ä¹ĭ家
    -0.10
    stead
    -0.10
    pcf
    -0.10
    orama
    -0.10
    ailer
    -0.10
    ä¾
    -0.10
    ãģĦãģĭ
    -0.09
    --------------------------------------------------------------------------↵
    -0.09
    YLON
    -0.09
    åŁĻ
    -0.09
    POSITIVE LOGITS
     dõi
    0.11
     experts
    0.09
    岸
    0.09
     our
    0.09
    åºĻ
    0.09
    æľĢæĸ°çļĦ
    0.08
    æĿĥå¨ģ
    0.08
    ä¸ĵ家
    0.08
    éĩįéĩį
    0.08
     my
    0.08
    Activations Density 0.026%

    No Known Activations