© 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. 53132
    Prev
    Next
    INDEX
    Explanations

    operation failed

    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
    æĸĻ
    -0.09
    icap
    -0.09
     batching
    -0.09
    /loader
    -0.08
    resp
    -0.08
    ped
    -0.08
     pedal
    -0.08
    gnu
    -0.08
     discipline
    -0.08
    éĶ¯
    -0.08
    POSITIVE LOGITS
    æĪIJåĬŁçļĦ
    0.12
    失败
    0.10
    éģĺ
    0.10
    çļĦæĪIJåĬŁ
    0.10
    顺åĪ©
    0.10
    WithError
    0.10
     attempted
    0.10
    åľ°å½¢
    0.09
    æīĺ
    0.09
    å°ijå¹´
    0.09
    Activations Density 0.242%

    No Known Activations