© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35938
    Prev
    Next
    INDEX
    Explanations

    .espresso technologies or neuroscience

    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
    abb
    -0.08
     abb
    -0.08
    _objs
    -0.08
    æĹłç¼ĺ
    -0.08
     convers
    -0.08
     forc
    -0.07
     Abb
    -0.07
    hin
    -0.07
     kernels
    -0.07
    paces
    -0.07
    POSITIVE LOGITS
    .esp
    0.10
    ween
    0.10
    ç¼ij
    0.10
    èĿĩ
    0.10
    æł²
    0.09
    ç¢ĵ
    0.09
    .gdx
    0.09
    åIJİéĿ¢çļĦ
    0.09
    .espresso
    0.09
    ä¸ªå·¥ä½ľ
    0.09
    Activations Density 0.065%

    No Known Activations