© 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. 62145
    Prev
    Next
    INDEX
    Explanations

    for your

    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
     Eisen
    -0.10
    å·«
    -0.09
    ä¸įåıĺ
    -0.09
    åħ¬è®¤
    -0.09
    æľºä¼ļ
    -0.08
    èģ¯åIJĪ
    -0.08
    Ñīе
    -0.08
     ÑģебÑı
    -0.08
    orea
    -0.08
    PURE
    -0.08
    POSITIVE LOGITS
    æŃ
    0.09
    æĦı大
    0.09
    åĽłåľ°
    0.09
    thing
    0.09
    æīĢåľ¨åľ°
    0.09
    lyn
    0.09
    è¿ĩå¤ļ
    0.09
    丢失
    0.09
    ä¹ŁæĹłæ³ķ
    0.09
    æѤ类
    0.08
    Activations Density 0.005%

    No Known Activations