© 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. 27732
    Prev
    Next
    INDEX
    Explanations

    anticipation or looking forward

    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
    æ´Ĵ
    -0.09
    ä¸įåIJĮç¨ĭ度
    -0.09
    èµĦ
    -0.09
    å®īåħ¨
    -0.08
    çłĴ
    -0.08
    çĽħ
    -0.08
    äºĨä¸Ģ
    -0.08
     lẽ
    -0.08
    çļĦæĦıä¹ī
    -0.08
    æĺ¯éĿŀ
    -0.08
    POSITIVE LOGITS
    çľĭåĪ°
    0.10
    çľĭè§ģ
    0.10
    åIJ¬åIJ¬
    0.10
    ä¸ĭä¸Ģ个
    0.10
    éºŁ
    0.09
    å¾Ģä¸Ĭ
    0.09
    åIJ¬è§ģ
    0.09
    æĿ¥çľĭ
    0.09
    /gallery
    0.09
    è¾ķ
    0.09
    Activations Density 0.004%

    No Known Activations