© 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. 1914
    Prev
    Next
    INDEX
    Explanations

    periodontal tissue, regeneration, probing depth

    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
    ç²¾
    -0.10
    æĤŃ
    -0.10
    .dp
    -0.10
    æĿ¥å®¾
    -0.09
    rams
    -0.09
    椿
    -0.09
    åī©ä¸ĭ
    -0.09
     chÃło
    -0.09
    æİ¥è¿ij
    -0.08
    cue
    -0.08
    POSITIVE LOGITS
    оÑĢо
    0.09
    è°ħ
    0.09
     Bass
    0.09
     accur
    0.09
    eker
    0.08
    éŃħ
    0.08
    /fs
    0.08
    AIM
    0.08
    罨
    0.08
    [assembly
    0.08
    Activations Density 0.154%

    No Known Activations