© 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. 47907
    Prev
    Next
    INDEX
    Explanations

    Prince, Lorde, Madonna, Adele

    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
    aine
    -0.09
    溥
    -0.09
    Ñĥв
    -0.08
    èł¹
    -0.08
    ãģĹãģĭãģªãģĦ
    -0.08
    tera
    -0.08
    ç«£
    -0.08
    åī
    -0.08
    åĶ¯
    -0.08
    iga
    -0.08
    POSITIVE LOGITS
    æµ´
    0.11
    æ¼Ĩ
    0.11
    é²ľ
    0.09
    uffers
    0.09
    elyn
    0.09
    æĴ°
    0.09
    ishment
    0.09
    (tol
    0.08
    åħīæĺİ
    0.08
    é¦Ī
    0.08
    Activations Density 0.047%

    No Known Activations