© 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. 39753
    Prev
    Next
    INDEX
    Explanations

    diligence, diligently, vigilance, zeal

    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
    tempt
    -0.10
    强çĥĪçļĦ
    -0.09
    æģ¯
    -0.09
    ision
    -0.09
    幸ç¦ıæĦŁ
    -0.09
    Cancelable
    -0.08
    强çĥĪ
    -0.08
    夺
    -0.08
    jÄĻ
    -0.08
    温æĥħ
    -0.08
    POSITIVE LOGITS
    颦
    0.11
    ently
    0.10
    ously
    0.10
    affer
    0.09
    erna
    0.09
    ORS
    0.09
    inded
    0.09
    rious
    0.09
    -minded
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    Activations Density 0.004%

    No Known Activations