© 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. 5302
    Prev
    Next
    INDEX
    Explanations

    mouth and related words

    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
    anter
    -0.11
    å§Ķ书记
    -0.10
    æĮĩå°ĸ
    -0.09
    èĦļä¸ĭ
    -0.09
    æĦıä¹īä¸Ĭ
    -0.09
    ëĬIJ
    -0.09
    身æĹģ
    -0.09
    /front
    -0.09
    å¢Ģ
    -0.08
    ợi
    -0.08
    POSITIVE LOGITS
    ful
    0.12
    -mouth
    0.11
    sWith
    0.11
    zelf
    0.10
    LESS
    0.10
    è¯Ģ
    0.10
    ted
    0.10
    ward
    0.09
    shake
    0.09
    iness
    0.09
    Activations Density 0.029%

    No Known Activations