© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52813
    Prev
    Next
    INDEX
    Explanations

    winner or crowned champion

    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
    æĿ¡
    -0.10
    ellt
    -0.09
    èĩªåѦ
    -0.09
    å¤Ł
    -0.08
     clo
    -0.08
    次è¦ģ
    -0.08
    å±Ģ
    -0.08
    å±Ģåī¯å±Ģéķ¿
    -0.08
    交åıĭ
    -0.08
    俱
    -0.08
    POSITIVE LOGITS
    赢家
    0.20
     winner
    0.17
     winners
    0.17
    _winner
    0.15
    winner
    0.15
     Winner
    0.14
    èĥľ
    0.14
    èĥľè´Ł
    0.14
    åĭĿ
    0.14
    Winner
    0.14
    Activations Density 0.312%

    No Known Activations