© 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. 49199
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE html

    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
    èªįãĤģ
    -0.10
    èĢģæĿ¿
    -0.09
    cum
    -0.09
    ä¸įçĪ±
    -0.09
    tÃł
    -0.09
     INDIRECT
    -0.09
    lä
    -0.08
    ãģĮãĤī
    -0.08
     pertinent
    -0.08
    驾车
    -0.08
    POSITIVE LOGITS
    Ëĭ
    0.08
    çĿĽ
    0.08
    weets
    0.08
    鹧
    0.08
    agens
    0.08
    zin
    0.08
    åĽ½åºĨ
    0.08
    鹦
    0.08
    sweet
    0.08
    Sweet
    0.08
    Activations Density 0.006%

    No Known Activations