© 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. 58034
    Prev
    Next
    INDEX
    Explanations

    T cell or B cell

    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
    nya
    -0.09
    âĶ
    -0.08
    in
    -0.08
    ting
    -0.08
    elon
    -0.08
    çļĭ
    -0.08
    Ñĭ
    -0.08
    omorphic
    -0.08
    æľ¬èº«çļĦ
    -0.08
    er
    -0.07
    POSITIVE LOGITS
    0.11
    ç»ıå¼Ģ
    0.11
    vidence
    0.09
    æĭŃ
    0.09
    ç²²
    0.09
    VERS
    0.09
    space
    0.09
    imestep
    0.09
    æĢį
    0.08
    éĶ·
    0.08
    Activations Density 0.905%

    No Known Activations