© 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. 34763
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    篦
    -0.09
    ä¸ĭ游
    -0.09
    ç¥ŀ
    -0.09
     pant
    -0.09
    åĵĩ
    -0.08
    Descriptor
    -0.08
     Pant
    -0.08
    enses
    -0.08
    æħ¢æħ¢çļĦ
    -0.08
    çĽį
    -0.08
    POSITIVE LOGITS
    æı¡
    0.13
    èĪĴéĢĤ
    0.12
    æı¡ä½ı
    0.11
    æĪIJ年人
    0.10
    æī§
    0.10
    åĿIJ
    0.10
     grip
    0.09
    åħ¥æīĭ
    0.09
     Comfort
    0.09
    æĮĪ
    0.09
    Activations Density 0.047%

    No Known Activations