© 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. 62048
    Prev
    Next
    INDEX
    Explanations

    photographing and shooting

    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
     gif
    -0.09
    ye
    -0.09
    æijĨ
    -0.09
    æĿ¿
    -0.08
     Paint
    -0.08
     pts
    -0.08
    Abort
    -0.08
    羣çĪ±
    -0.08
     sticker
    -0.08
     Animator
    -0.08
    POSITIVE LOGITS
    óc
    0.11
    æijĦ
    0.10
    elper
    0.10
    åŃ£èĬĤ
    0.10
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    ODO
    0.09
    _TestCase
    0.09
    PropertyParams
    0.09
    _sta
    0.09
    comm
    0.09
    Activations Density 0.107%

    No Known Activations