© 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. 1312
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing information

    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
    è¡ĢèĦī
    -0.09
    å°ģéĿ¢
    -0.08
    èŀºæĹĭ
    -0.08
    åīįä¸ī
    -0.08
    .protobuf
    -0.08
    幺
    -0.08
    (nameof
    -0.07
    .setMaximum
    -0.07
    .newBuilder
    -0.07
    ocr
    -0.07
    POSITIVE LOGITS
    åµĮ
    0.10
    çľ©
    0.10
    izr
    0.10
    JS
    0.09
     clearTimeout
    0.09
     div
    0.08
    .jquery
    0.08
    æĬĹåĩ»
    0.08
    éĴ»çłĶ
    0.08
     JS
    0.08
    Activations Density 3.547%

    No Known Activations