© 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. 33780
    Prev
    Next
    INDEX
    Explanations

    one noun / quantifier of

    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
     Gallagher
    -0.09
     Cousins
    -0.08
    agers
    -0.08
    _$_
    -0.08
     closest
    -0.08
    strate
    -0.08
    ucid
    -0.08
    åĩºèī²
    -0.08
    ieves
    -0.08
    undy
    -0.07
    POSITIVE LOGITS
     of
    0.17
     của
    0.14
    à¸Ĥà¸Ńà¸ĩ
    0.14
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.13
     delle
    0.10
    ERA
    0.10
    è¿Ļåħ¶ä¸Ń
    0.09
     thereof
    0.09
    umper
    0.09
     degli
    0.09
    Activations Density 0.223%

    No Known Activations