© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    ie

    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
    å°¼äºļ
    -0.10
    uhn
    -0.10
    omer
    -0.09
     pretend
    -0.08
    ç¥ī
    -0.08
     Adams
    -0.08
    ught
    -0.08
    é«ĺåİŁ
    -0.08
    upert
    -0.08
    æŀĦ
    -0.08
    POSITIVE LOGITS
    橹
    0.10
    伧
    0.09
    /Library
    0.09
    تا
    0.09
    ä¾¥
    0.09
     пÑĢим
    0.09
    ä¸Ģå¾ĭ
    0.09
    andom
    0.09
    缸åħ³æĸ°éĹ»
    0.09
    踩
    0.08
    Activations Density 0.009%

    No Known Activations