© 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. 19506
    Prev
    Next
    INDEX
    Explanations

    you give / share / tell

    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
    åħ¸åŀĭ
    -0.10
    æľĢå¿«
    -0.09
    ä¸įåıĺ
    -0.09
    æ»´
    -0.09
    éħ¾
    -0.09
    å·²ä¹ħçļĦ
    -0.08
    æĪĴ
    -0.08
    æĮ¤
    -0.08
    law
    -0.08
    _DYNAMIC
    -0.08
    POSITIVE LOGITS
    èIJ½åħ¥
    0.10
    bler
    0.09
    éĢīæĭ©äºĨ
    0.09
    дÑĥÑĤ
    0.09
    æijĨåľ¨
    0.09
    çĽ²çĽ®
    0.09
    æĶ¾æīĭ
    0.09
    å¨ģå°Ķ
    0.09
     blindly
    0.09
    æĵ¬
    0.08
    Activations Density 0.048%

    No Known Activations