© 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. 17420
    Prev
    Next
    INDEX
    Explanations

    barb names and endings

    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
    iphy
    -0.10
    opi
    -0.10
    Ø«ÙĦ
    -0.10
    ibling
    -0.10
    æªĶ
    -0.09
    idences
    -0.08
    AAP
    -0.08
    upt
    -0.08
    cept
    -0.08
    è°´
    -0.08
    POSITIVE LOGITS
    èĩ¬
    0.10
    sWith
    0.10
    ä¸ĢåĪĩ
    0.09
     Ñģобой
    0.09
    åĩłåı¥
    0.09
    icum
    0.09
    icular
    0.09
    ages
    0.09
    orno
    0.08
    ../../../
    0.08
    Activations Density 0.006%

    No Known Activations