© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    paste formulation

    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
     Nie
    -0.09
    alyzed
    -0.09
    aldo
    -0.08
    à¹Ģà¸ģาะ
    -0.08
    oriously
    -0.08
    æİł
    -0.08
    ëĭ¬
    -0.08
     ann
    -0.08
     Metallic
    -0.08
    rev
    -0.08
    POSITIVE LOGITS
    æīĪ
    0.10
    æ²®
    0.10
    èĮ§
    0.09
    宪
    0.09
    æĽ´å¤ļ精彩
    0.09
    æIJŀ好
    0.09
    æĥłæ°ij
    0.09
    ãģĹãģ¾
    0.08
    inne
    0.08
    éľĩåĬ¨
    0.08
    Activations Density 0.150%

    No Known Activations