© 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. 58890
    Prev
    Next
    INDEX
    Explanations

    streaming and transmission

    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
    éķĽ
    -0.11
    æ¿
    -0.10
    .vert
    -0.10
    pta
    -0.09
    éĴĬ
    -0.09
    ulators
    -0.09
    ç»Łè®¡
    -0.09
    转移åĪ°
    -0.09
    åħ·å¤ĩ
    -0.09
    ambi
    -0.09
    POSITIVE LOGITS
    ç´łæĿIJ
    0.10
    çļĦåij½è¿IJ
    0.10
    çľģåħ¬å®īåİħ
    0.09
    æľĪä¸ĭ
    0.08
    çľģåĨħ
    0.08
    妻
    0.08
    ä¸įå¿į
    0.08
    干线
    0.08
    示èĮĥåŁºåľ°
    0.08
    ior
    0.08
    Activations Density 0.072%

    No Known Activations