© 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. 54634
    Prev
    Next
    INDEX
    Explanations

    degree of X

    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
    ellaneous
    -0.11
    rust
    -0.10
    ayas
    -0.09
    isser
    -0.09
    ellan
    -0.09
    aya
    -0.09
    ome
    -0.09
    ä¿Ĺè¯Ŀ说
    -0.09
     дела
    -0.09
    ready
    -0.09
    POSITIVE LOGITS
     Celsius
    0.11
    åIJĪãģĦ
    0.11
     ØŃر
    0.11
    edList
    0.11
     Fahrenheit
    0.10
     вÑĭÑĢажен
    0.10
    ording
    0.10
    ément
    0.09
    ãĤľ
    0.09
    veloper
    0.09
    Activations Density 0.048%

    No Known Activations