© 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. 11315
    Prev
    Next
    INDEX
    Explanations

    accessory, an

    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
    endor
    -0.10
    OLF
    -0.09
    款
    -0.09
    å¦ĤæĦı
    -0.09
    è´µ
    -0.08
    iny
    -0.08
    åIJĮäºĭ
    -0.08
    rons
    -0.08
    åįļè§Ī
    -0.08
    åĿļåĨ³
    -0.08
    POSITIVE LOGITS
    è´´
    0.10
    åıĭæĥħ
    0.09
    çĶľç¾İ
    0.09
    éħįå¥Ĺ
    0.09
    å·´æĭī
    0.09
    .xhtml
    0.09
    妫
    0.09
    _operator
    0.09
    缸åºĶçļĦ
    0.09
    è²¼
    0.09
    Activations Density 0.050%

    No Known Activations