© 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. 57996
    Prev
    Next
    INDEX
    Explanations

    colon or comma

    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
    abel
    -0.08
    ua
    -0.08
    ä¸ĢåĪĩ
    -0.08
    ancy
    -0.07
    åıªä¼ļ
    -0.07
    ä¹ĭéģĵ
    -0.07
     wherever
    -0.07
    èĦ±ç¦»
    -0.07
    å¹²äºĭ
    -0.07
    空çĻ½
    -0.07
    POSITIVE LOGITS
    utton
    0.10
    æĥ³æī¾
    0.09
    æĸ§
    0.09
    åİĿ
    0.09
    ewis
    0.09
    åĩ«
    0.09
    ä¸įåIJĮæĦı
    0.09
    igu
    0.09
    ests
    0.09
    edin
    0.09
    Activations Density 0.011%

    No Known Activations