© 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. 37826
    Prev
    Next
    INDEX
    Explanations

    all-powerful Almighty God

    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
    èįĨ
    -0.09
    è´¼
    -0.09
    åĩij
    -0.09
    ross
    -0.09
     ren
    -0.08
    åŃĿ
    -0.08
    æĬ¢
    -0.08
    _fixture
    -0.08
    è¹ī
    -0.08
    ç«¥
    -0.08
    POSITIVE LOGITS
    ä¸Ĭå¸Ŀ
    0.12
    åģļä¸įåĪ°
    0.10
    èĥ½åĬĽåĴĮ
    0.10
    ŀæĢ§
    0.10
    é£ĺ
    0.10
    _ATTRIBUTE
    0.09
    æı½
    0.09
    åĩ¼
    0.09
    åĬŁåĬĽ
    0.09
    éĽĦåİļ
    0.09
    Activations Density 0.040%

    No Known Activations