© 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. 23173
    Prev
    Next
    INDEX
    Explanations

    evidence and facts

    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
    iali
    -0.10
    ä¸įå®ľ
    -0.09
    æģŃåĸľ
    -0.09
    ialis
    -0.09
    è¶ħé¢Ŀ
    -0.09
     consec
    -0.08
    çİ
    -0.08
    toolbox
    -0.08
     WARRANTIES
    -0.08
    Immediately
    -0.08
    POSITIVE LOGITS
    èµĦæĸĻ
    0.19
    è¯ģæį®
    0.15
     evidence
    0.14
    èµĦæĸĻæĺ¾ç¤º
    0.14
     facts
    0.14
    è³ĩæĸĻ
    0.14
     available
    0.13
    åı²æĸĻ
    0.13
    ç¿Ķ
    0.12
    大éĩıçļĦ
    0.11
    Activations Density 0.065%

    No Known Activations