© 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. 55481
    Prev
    Next
    INDEX
    Explanations

    drawing paths and shapes

    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
    IDES
    -0.10
    äºĨä¸Ģ份
    -0.09
    IDE
    -0.09
    æķŀ
    -0.09
    ide
    -0.09
    éªł
    -0.09
    çļĦæĢĿæĥ³
    -0.08
    磮
    -0.08
    触åıij
    -0.08
    å±
    -0.08
    POSITIVE LOGITS
    eson
    0.09
    esson
    0.09
    ä¼Ĭæĭī
    0.09
    etro
    0.09
    纹
    0.09
    èĹĿ
    0.09
    æĪĴ
    0.09
    åIJĪä½ľåħ±èµ¢
    0.09
    è¿ĩ滤
    0.08
    åĪģ
    0.08
    Activations Density 0.097%

    No Known Activations