© 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. 18388
    Prev
    Next
    INDEX
    Explanations

    TNA talents

    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
    ç²¾éĢļ
    -0.10
    ory
    -0.09
    iveness
    -0.09
    endra
    -0.09
     Turnbull
    -0.09
     меÑģÑıÑĨ
    -0.08
    é½IJåħ¨
    -0.08
     fet
    -0.08
    æ¡IJ
    -0.08
    åħ³éŨ
    -0.08
    POSITIVE LOGITS
    Bindable
    0.10
    æĦı大
    0.09
    roe
    0.09
    éĤ¸
    0.09
    ieri
    0.09
    vÃŃ
    0.09
    åħħ
    0.09
    èľ
    0.09
    ry
    0.08
    zos
    0.08
    Activations Density 0.002%

    No Known Activations