© 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. 26433
    Prev
    Next
    INDEX
    Explanations

    owel combinations followed by letters

    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
    	TokenName
    -0.14
    <<<<
    -0.12
    ively
    -0.11
    <<<<<<<<
    -0.10
    ä¼ļåIJĮ
    -0.09
    ivity
    -0.09
    Ãło
    -0.09
    ÑĦи
    -0.09
     Ñģобой
    -0.09
    OMIC
    -0.09
    POSITIVE LOGITS
    orld
    0.16
    riting
    0.13
    ski
    0.13
    ings
    0.12
    ORLD
    0.12
    renc
    0.12
    rence
    0.12
    ness
    0.12
    esome
    0.12
    sville
    0.11
    Activations Density 0.327%

    No Known Activations