© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7597
    Prev
    Next
    INDEX
    Explanations

    giovanni | giuseppe | giacomo | gianni

    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
    ilha
    -0.10
    åħ¨å®¶
    -0.09
    inium
    -0.09
    anus
    -0.09
    ÇĴ
    -0.09
    åŃIJåŃĻ
    -0.09
    rans
    -0.09
    åħ¨æł¡
    -0.08
    åħ¨åijĺ
    -0.08
    Ñģов
    -0.08
    POSITIVE LOGITS
     prox
    0.09
    讨
    0.09
    filtr
    0.09
    outs
    0.09
    馥
    0.08
    çļĦæķ´ä½ĵ
    0.08
    otten
    0.08
    ann
    0.08
    æį£
    0.08
    éĤ£ä¸ªäºº
    0.08
    Activations Density 0.031%

    No Known Activations