© 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. 48479
    Prev
    Next
    INDEX
    Explanations

    the arrow

    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
    纺
    -0.10
    æī¶
    -0.09
     Ñģобой
    -0.09
    ëĭ¨
    -0.09
    å®ĮæĪIJåIJİ
    -0.08
    ç¾²
    -0.08
    stag
    -0.08
    å¸Ĩ
    -0.08
    åħ³éĶ®æĺ¯
    -0.08
    æĺİæĺİ
    -0.08
    POSITIVE LOGITS
    ewan
    0.11
    ä¸ĺ
    0.09
     пед
    0.09
     synced
    0.08
    ç«ł
    0.08
    éĽķ
    0.08
    ä¸į容æĺĵ
    0.08
    æĬķèµĦé¢Ŀ
    0.08
    èĩªå·±åĸľæ¬¢
    0.08
     mic
    0.08
    Activations Density 0.023%

    No Known Activations