© 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. 19801
    Prev
    Next
    INDEX
    Explanations

    times the

    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
    æĪijçļĦå¿ĥ
    -0.09
    incess
    -0.08
    инг
    -0.08
    æĽ´å¤ļ
    -0.08
    å¼±
    -0.08
    åĬ¾
    -0.08
    贯彻
    -0.07
    ÑģÑĤÑĢ
    -0.07
    åĽłåľ°
    -0.07
    \$
    -0.07
    POSITIVE LOGITS
    åģļçļĦäºĭ
    0.11
    åģļçļĦäºĭæĥħ
    0.10
    anca
    0.10
    arning
    0.09
    åIJģ
    0.09
    æĶ¶çº³
    0.09
    æĢĽ
    0.09
    IOD
    0.09
    æµģæ°´
    0.09
    .resolution
    0.08
    Activations Density 0.012%

    No Known Activations