© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50372
    Prev
    Next
    INDEX
    Explanations

    opportunity employer, package err, other brilliant

    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
    èµĽ
    -0.10
    ä¼ļè§ģ
    -0.10
    审
    -0.09
     KY
    -0.09
    å§ĵ
    -0.09
    æī¹åĩĨ
    -0.09
    .hl
    -0.08
    çļĦåķĨåĵģ
    -0.08
    vens
    -0.08
    match
    -0.08
    POSITIVE LOGITS
    eln
    0.11
    建档
    0.09
    ä¸įæĢķ
    0.09
    éĥijéĩį
    0.09
    主æŨ
    0.09
    ç§ĭ
    0.09
     deb
    0.09
    æ¼Ķ讲
    0.08
     Laf
    0.08
     originals
    0.08
    Activations Density 0.011%

    No Known Activations