© 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. 28056
    Prev
    Next
    INDEX
    Explanations

    ensure that

    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
    uh
    -0.09
    éĢłæĪIJçļĦ
    -0.09
    ازÙĬ
    -0.09
    ework
    -0.09
    讲究
    -0.08
    好似
    -0.08
    åĨĴéĻ©
    -0.08
    èĪįå¾Ĺ
    -0.08
    éĹªéĹª
    -0.08
    ا
    -0.08
    POSITIVE LOGITS
    ably
    0.11
     Ñģебе
    0.11
     contato
    0.10
    emente
    0.10
     rằng
    0.10
     гаÑĢан
    0.09
     гаÑĢанÑĤи
    0.09
    LAG
    0.09
    IONS
    0.09
    è´¿èµĤ
    0.09
    Activations Density 0.037%

    No Known Activations