© 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. 38731
    Prev
    Next
    INDEX
    Explanations

    actually

    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
    人为
    -0.10
    å¿«æĿ¥
    -0.10
    å¹²èĦĨ
    -0.09
    è¿Ļäºĭ
    -0.09
    åħ±äº«
    -0.09
    å¿«
    -0.09
    é¦ĸåħĪè¦ģ
    -0.09
    æĹ¢æĺ¯
    -0.09
    åħĪæĺ¯
    -0.09
    èĥĿ
    -0.08
    POSITIVE LOGITS
     underlying
    0.13
    å®ŀéĻħä¸Ĭ
    0.12
    èĥĮåIJİçļĦ
    0.12
     actually
    0.11
    åĨħ涵
    0.11
     unseen
    0.11
    å®Łãģ¯
    0.11
    åį´æĺ¯
    0.11
    ç§ģä¸ĭ
    0.11
     Actually
    0.11
    Activations Density 0.087%

    No Known Activations