© 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. 62616
    Prev
    Next
    INDEX
    Explanations

    invaluable, indispensable

    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
    ious
    -0.09
    å¦ĤæŀľæĪij们
    -0.08
    ราว
    -0.08
    imus
    -0.08
    tu
    -0.08
    ilee
    -0.08
    é«ĺæ½®
    -0.08
     Ghost
    -0.08
    inox
    -0.08
    iken
    -0.07
    POSITIVE LOGITS
    IMUM
    0.10
    æĬĢæľ¯æľįåĬ¡
    0.10
    è°Ģ
    0.10
    æ¡ħ
    0.10
    -bs
    0.09
    alysis
    0.09
    è¯ĥ
    0.09
    æĭĦ
    0.09
    å¿ħä¸įåı¯
    0.09
     Stap
    0.09
    Activations Density 0.006%

    No Known Activations