© 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. 19991
    Prev
    Next
    INDEX
    Explanations

    Vogues and names like Vogel

    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
    踵
    -0.11
    æīĵ好
    -0.10
    æł¼å°Ķ
    -0.09
    holding
    -0.09
    ORIES
    -0.08
    éħ
    -0.08
    rench
    -0.08
    hog
    -0.08
    ament
    -0.08
    éĺ¡
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.10
    er
    0.10
    yard
    0.10
    ered
    0.10
    eer
    0.09
    ing
    0.08
    ãĤīãģĽ
    0.08
    gable
    0.08
    eding
    0.08
    lets
    0.08
    Activations Density 0.003%

    No Known Activations