© 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. 54380
    Prev
    Next
    INDEX
    Explanations

    victory over an opponent

    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
    ings
    -0.13
    åĦ¿
    -0.13
    lessly
    -0.10
    ify
    -0.10
    ers
    -0.10
    oe
    -0.09
    ness
    -0.09
    imen
    -0.09
    ifier
    -0.09
    out
    -0.08
    POSITIVE LOGITS
    naire
    0.13
    zelf
    0.10
    eer
    0.10
    女ç¥ŀ
    0.10
    iona
    0.09
    lü
    0.09
    è¡Ĺä¸Ĭ
    0.09
    боÑĤ
    0.09
    èĢħçļĦ
    0.09
    FUL
    0.09
    Activations Density 0.006%

    No Known Activations