© 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. 2369
    Prev
    Next
    INDEX
    Explanations

    roman numerals

    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
    ../
    -0.12
    like
    -0.11
    HING
    -0.10
    net
    -0.10
    åĩij
    -0.09
    rique
    -0.09
    s
    -0.09
    ../../../
    -0.09
    line
    -0.08
    ãģıãĤĮ
    -0.08
    POSITIVE LOGITS
    irty
    0.12
    enge
    0.11
    izard
    0.10
    antas
    0.10
    มà¸Ńà¸ĩ
    0.10
    aries
    0.09
    leck
    0.09
    жд
    0.09
    annis
    0.09
    ities
    0.09
    Activations Density 0.073%

    No Known Activations