© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    clothing item skirt

    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
    ¤
    -0.10
    èĮ§
    -0.09
    lsen
    -0.09
    udded
    -0.09
    æѤåĪ»
    -0.09
    itate
    -0.08
    å¤±çľł
    -0.08
    å¿«æĬ¥
    -0.08
    ague
    -0.08
    petition
    -0.08
    POSITIVE LOGITS
    ably
    0.13
    ï¸
    0.10
    èĩ¾
    0.10
    writers
    0.10
    说æĺ¯
    0.10
    ural
    0.10
    ler
    0.09
    IPP
    0.09
    edList
    0.08
    å²Ń
    0.08
    Activations Density 0.002%

    No Known Activations