© 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. 49476
    Prev
    Next
    INDEX
    Explanations

    quantifying change or magnitude

    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
    iams
    -0.10
    unt
    -0.09
    å¾Ī好
    -0.09
    CACHE
    -0.08
     Serg
    -0.08
    çŁ¢
    -0.08
    uti
    -0.08
    ä¸ĩä¸Ģ
    -0.08
     Miche
    -0.08
     Hogan
    -0.08
    POSITIVE LOGITS
    姬
    0.10
    ahead
    0.09
    ally
    0.09
    ä¸Ģ次æĢ§
    0.09
    éĶı
    0.09
    èIJ½åIJİ
    0.09
    éģıåĪ¶
    0.09
    ç¨Ķ
    0.09
    æ¯ĶæĪij
    0.09
    çĶŁæ´»è´¨éĩı
    0.08
    Activations Density 0.029%

    No Known Activations