© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    synthetic aperture

    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
    åħħ
    -0.09
    éĸĵãģ«
    -0.09
    èľĤ
    -0.08
    ä¸įåłª
    -0.08
    åĥŃ
    -0.08
    æ¶Ī
    -0.08
    å»Ĭ
    -0.08
    itar
    -0.08
    å½·
    -0.08
    çħ¤
    -0.08
    POSITIVE LOGITS
    ateau
    0.10
    åĨ·éĵ¾çī©æµģ
    0.09
    åºķå±Ĥ
    0.09
    .surface
    0.09
    æ°´éĿ¢
    0.09
    Proto
    0.09
    uzzi
    0.09
    èĮ«èĮ«
    0.08
    apia
    0.08
    ستاÙĨ
    0.08
    Activations Density 0.036%

    No Known Activations