© 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. 34089
    Prev
    Next
    INDEX
    Explanations

    combining expertise and technology

    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
    åĬŁå¤«
    -0.09
    esh
    -0.09
    è¿Ļç§įæĸ¹å¼ı
    -0.08
    è¶Ĭ
    -0.08
    ather
    -0.08
     clarified
    -0.08
    æīĵäºĨ
    -0.08
    ouch
    -0.08
    imes
    -0.08
     success
    -0.07
    POSITIVE LOGITS
    äºĴè¡¥
    0.13
    åIJĪ并
    0.12
    èµĦæºIJæķ´åIJĪ
    0.11
    combine
    0.10
    带ç»Ļ
    0.10
    æĽ´å¼º
    0.10
    两æīĭ
    0.09
    æĪ·åı£
    0.09
    å®ħ
    0.09
    åľ°åŁŁ
    0.09
    Activations Density 0.219%

    No Known Activations