© 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. 33582
    Prev
    Next
    INDEX
    Explanations

    caffeine and coffee related terms

    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
    inqu
    -0.09
    isos
    -0.08
     Datum
    -0.08
    åĽŀ头
    -0.08
    åŃĺåľ¨çļĦ
    -0.08
    spiel
    -0.08
     бÑĭÑģÑĤÑĢо
    -0.08
    &
    -0.08
    v
    -0.07
     aff
    -0.07
    POSITIVE LOGITS
    даÑİÑĤ
    0.10
    丼æŀĹ
    0.10
    饺
    0.09
    é©·
    0.09
    IRS
    0.09
    ãģ¨ãģ«ãģĭãģı
    0.09
    _disk
    0.09
    itive
    0.09
    ðŁı»
    0.09
    ofday
    0.09
    Activations Density 0.004%

    No Known Activations