© 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. 30713
    Prev
    Next
    INDEX
    Explanations

    bash shell commands

    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
     Lawson
    -0.10
    ONUS
    -0.10
    obl
    -0.10
    onus
    -0.09
    æ¤į
    -0.09
    fern
    -0.09
    markt
    -0.09
    æ¹®
    -0.09
    è¾Ľåĭ¤
    -0.09
    åĩºæīĭ
    -0.09
    POSITIVE LOGITS
    æ¯ı人
    0.10
    èĪ±
    0.09
    äºķ
    0.09
    æ³Ĭ
    0.09
     ÑĤек
    0.09
     Inv
    0.09
    临港
    0.09
    дÑĥ
    0.08
    èĩŃ
    0.08
    _INV
    0.08
    Activations Density 0.263%

    No Known Activations