© 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. 34250
    Prev
    Next
    INDEX
    Explanations

    perl code

    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
    eden
    -0.10
    à¦
    -0.10
    æķ·
    -0.10
    åıĹåĪ°äºĨ
    -0.09
    笮
    -0.09
    неж
    -0.09
    é«ĺæĸ°æĬĢæľ¯
    -0.09
    æľĽ
    -0.09
    ward
    -0.09
     Casc
    -0.09
    POSITIVE LOGITS
    æĺ¯æĪij
    0.09
    éĴī
    0.09
    鼩
    0.08
    Foo
    0.08
    TestData
    0.08
    ç§Łè½¦
    0.08
     completeness
    0.08
    .Modules
    0.08
    èĽĭ
    0.08
    èģªæĺİ
    0.08
    Activations Density 0.126%

    No Known Activations