© 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. 50079
    Prev
    Next
    INDEX
    Explanations

    a common phrase

    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
     Ost
    -0.10
    大çĽĺ
    -0.09
    kaar
    -0.08
    æĹłç§ģ
    -0.08
    _snd
    -0.08
    缸è¾ĥ
    -0.08
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.08
     ëĮ
    -0.08
    ldr
    -0.08
    Ñģов
    -0.08
    POSITIVE LOGITS
    è§ĨåIJ¬
    0.09
    æĪijåıĪ
    0.09
    åıĬåħ¶
    0.09
    æĪijä¸į
    0.09
     UPC
    0.08
    æĪij没æľī
    0.08
    itis
    0.08
    æ¸
    0.08
    åį´ä¸į
    0.08
    è²ī
    0.08
    Activations Density 0.069%

    No Known Activations