© 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. 2904
    Prev
    Next
    INDEX
    Explanations

    magical entities and settings

    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¸ĢæĹı
    -0.09
    è¾°
    -0.09
    ä»
    -0.09
    æĭį
    -0.09
    èĪ°éĺŁ
    -0.08
    仪
    -0.08
     báo
    -0.08
    ³
    -0.08
    ä¸ĭæĿ¥çļĦ
    -0.08
    borg
    -0.08
    POSITIVE LOGITS
    zoom
    0.10
    ç©·
    0.10
    窮
    0.09
    fully
    0.09
     quar
    0.09
     disen
    0.09
    ä¹ĭ乡
    0.09
    eneg
    0.09
    .ld
    0.08
    UIColor
    0.08
    Activations Density 0.169%

    No Known Activations