© 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. 54214
    Prev
    Next
    INDEX
    Explanations

    explains why or how

    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
    åĸ
    -0.09
    æĴ·
    -0.09
    inally
    -0.09
    为ä¹ĭ
    -0.09
    éĹ´çļĦ
    -0.09
    å¾Ĺä½ı
    -0.09
    强çĥĪ
    -0.09
     Prev
    -0.09
    éĹ´
    -0.08
    ä¹ĭäºī
    -0.08
    POSITIVE LOGITS
    æĻ°
    0.12
     why
    0.11
     rằng
    0.11
    нÑİ
    0.09
    åijĺ
    0.09
    为ä½ķ
    0.09
     how
    0.09
    æ¸ħæ¥ļ
    0.09
    ä»Ģä¹Īåı«
    0.09
    ÑģÑı
    0.09
    Activations Density 0.019%

    No Known Activations