© 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. 33332
    Prev
    Next
    INDEX
    Explanations

    travel by

    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
    åŀ£
    -0.09
    çļĦ身ä½ĵ
    -0.09
    çļĦéĴ±
    -0.09
    eld
    -0.08
    çļĦçľ¼çĿĽ
    -0.08
    hores
    -0.08
    æĭ®
    -0.08
    æķ
    -0.08
    侬
    -0.08
    esc
    -0.08
    POSITIVE LOGITS
    lessly
    0.10
    via
    0.10
    人工
    0.10
     via
    0.10
    _via
    0.10
    çĶµè¯Ŀ
    0.10
    Via
    0.09
    秦çļĩ
    0.09
     عبر
    0.09
    _SMS
    0.09
    Activations Density 0.075%

    No Known Activations