© 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. 4078
    Prev
    Next
    INDEX
    Explanations

    long way to go

    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
    娥
    -0.10
    owan
    -0.09
    年级
    -0.09
    å¯ĵ
    -0.09
     Crane
    -0.09
     Uns
    -0.09
     Designed
    -0.09
    ä½ĵéªĮ
    -0.08
    æĥ§
    -0.08
    çķı
    -0.08
    POSITIVE LOGITS
    èī°å·¨
    0.17
    çļĦä»»åĬ¡
    0.13
    ä»»åĬ¡
    0.13
    说æľį
    0.13
    ä»»åĭĻ
    0.12
     task
    0.12
     задаÑĩ
    0.11
     tasks
    0.11
     challenges
    0.11
    èī°èĭ¦
    0.11
    Activations Density 0.181%

    No Known Activations