© 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. 11625
    Prev
    Next
    INDEX
    Explanations

    dashes and list items

    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
    æijĦ
    -0.09
    姶
    -0.08
    äºĨä¸Ģæī¹
    -0.08
    èĭ¥å¹²
    -0.08
    ä»Ĭå¹´
    -0.08
    hev
    -0.08
    wed
    -0.08
    åĨį说
    -0.08
    ISS
    -0.08
    åĿļå®ŀ
    -0.08
    POSITIVE LOGITS
    èĺħ
    0.09
    åı¯è°ĵæĺ¯
    0.09
    ä¸į论æĺ¯
    0.08
    èĭ¦
    0.08
    lease
    0.08
    ä¸Ģç¢Ĺ
    0.08
    å®ŀäºĭ
    0.08
    è¯ı
    0.08
    å©ķ
    0.08
    _LIBRARY
    0.08
    Activations Density 0.083%

    No Known Activations