© 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. 5138
    Prev
    Next
    INDEX
    Explanations

    expression of feeling or idea

    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
    abler
    -0.08
    atz
    -0.08
    æĦı大
    -0.08
    ätz
    -0.08
    LER
    -0.08
    çļĦ帮åĬ©
    -0.08
    _PARENT
    -0.08
    erval
    -0.08
    å©Ĩ
    -0.08
    å±ķçİ°åĩº
    -0.08
    POSITIVE LOGITS
     rằng
    0.10
    _mr
    0.09
    alse
    0.09
    æĿ¥åİĨ
    0.08
    åİī
    0.08
    ç²³
    0.08
    .jquery
    0.08
    æ²ĥ
    0.08
    å¾Ģ
    0.08
    ä»ĬåIJİ
    0.08
    Activations Density 0.014%

    No Known Activations