© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32699
    Prev
    Next
    INDEX
    Explanations

    current + specific noun

    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
    ä¸įç»ı
    -0.10
    éªŀ
    -0.09
    天天
    -0.09
    å¹´åĨħ
    -0.09
    _TER
    -0.09
    人æ°Ķ
    -0.09
    æĸ°äº§åĵģ
    -0.08
    uchs
    -0.08
     vert
    -0.08
    ENABLE
    -0.08
    POSITIVE LOGITS
     existing
    0.10
    amps
    0.09
    -existing
    0.09
    existing
    0.09
    çݰæľīçļĦ
    0.09
    çĬ¶åĨµ
    0.09
    Lines
    0.08
    çħ§æĺİ
    0.08
    çļĦ设计
    0.08
    çݰæľī
    0.08
    Activations Density 0.084%

    No Known Activations