© 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. 22551
    Prev
    Next
    INDEX
    Explanations

    extend, extends, extended, extending

    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
    åıijå±ķæĸ¹åIJij
    -0.09
    äºĨèµ·æĿ¥
    -0.09
    å¿ĺè®°
    -0.09
    社ä¼ļç»Ħç»ĩ
    -0.09
    enk
    -0.09
    åĽŀæĥ³
    -0.09
    åIJĦ级
    -0.08
    åĩ¼
    -0.08
    æĢ»ç»ĵ
    -0.08
    emes
    -0.08
    POSITIVE LOGITS
    延éķ¿
    0.17
    延伸
    0.17
     Extend
    0.14
     extend
    0.14
    extended
    0.14
     Extended
    0.13
    Extend
    0.13
     extended
    0.13
    Extended
    0.13
     extends
    0.13
    Activations Density 0.069%

    No Known Activations