© 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. 20266
    Prev
    Next
    INDEX
    Explanations

    clothes, outfits, attire

    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
    éŨæĪ·
    -0.10
    éĢĭ
    -0.09
    å´Ľ
    -0.09
    ÑĢид
    -0.09
    OwnProperty
    -0.09
    byn
    -0.09
    éŸ
    -0.08
    æĴĴ
    -0.08
    åijĬ
    -0.08
    .setParameter
    -0.08
    POSITIVE LOGITS
    è¡£æľį
    0.15
    ç©¿æĪ´
    0.15
    è¡£çī©
    0.15
    è¡£
    0.14
     одеж
    0.13
    æľį饰
    0.13
     attire
    0.12
     clothing
    0.11
     worn
    0.11
    裳
    0.11
    Activations Density 0.103%

    No Known Activations