© 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. 62204
    Prev
    Next
    INDEX
    Explanations

    tooth and dental topics

    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
    STITUTE
    -0.10
    å°¤åħ¶æĺ¯
    -0.10
    chor
    -0.10
    isse
    -0.09
    ções
    -0.09
    æīĢèĥ½
    -0.09
    æķ´è½¦
    -0.09
    änder
    -0.09
    ouve
    -0.09
    ãģĨãģ¾ãģı
    -0.09
    POSITIVE LOGITS
    ness
    0.10
    sWith
    0.10
    lg
    0.10
    fulness
    0.10
    ering
    0.10
    lf
    0.10
    less
    0.09
    line
    0.09
    lah
    0.09
    est
    0.09
    Activations Density 0.005%

    No Known Activations