© 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. 55197
    Prev
    Next
    INDEX
    Explanations

    for personalised guidance

    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
    icious
    -0.09
    åŃ©
    -0.09
    éĺĻ
    -0.09
    ä¸įé«ĺ
    -0.09
    å¾ĹçĽĬäºİ
    -0.09
    é¹Ħ
    -0.08
    æĪĸèĢħ说
    -0.08
    ä¸Ģéĥ¨åĪĨ
    -0.08
    æī¾åĪ°äºĨ
    -0.08
    许å¤ļ人
    -0.08
    POSITIVE LOGITS
    æĽ´å¥½çļĦ
    0.16
    æĽ´å¥½åľ°
    0.12
     better
    0.11
    æĽ´å¥½
    0.11
    è¿Ľä¸ĢæŃ¥
    0.10
    rray
    0.09
    æĽ´å¿«
    0.09
    amen
    0.09
    kart
    0.08
    edom
    0.08
    Activations Density 0.088%

    No Known Activations