© 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. 19280
    Prev
    Next
    INDEX
    Explanations

    membrane biology and properties

    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
    wick
    -0.10
    idge
    -0.09
    erm
    -0.09
    梢
    -0.09
    é£İåı£
    -0.09
    表çݰ为
    -0.09
    ¼
    -0.09
     обÑĢазом
    -0.09
    ек
    -0.09
    åķī
    -0.09
    POSITIVE LOGITS
    åİļåİļçļĦ
    0.09
    广大
    0.09
    lining
    0.09
    LESS
    0.08
    less
    0.08
    å¹¿æ³Ľ
    0.08
    -separated
    0.08
    ŀ
    0.08
    atee
    0.08
    ULAR
    0.08
    Activations Density 0.100%

    No Known Activations