© 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. 36264
    Prev
    Next
    INDEX
    Explanations

    in [attribute]

    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
    踽
    -0.10
    ä¸įå¿į
    -0.10
    åŀĽ
    -0.09
    éĻIJæľŁ
    -0.09
    ç²ķ
    -0.09
    ted
    -0.09
    æĤŃ
    -0.09
    ä¸įåħį
    -0.09
    ä¸į让
    -0.09
    åĪĨæĺİ
    -0.08
    POSITIVE LOGITS
     size
    0.12
     ÑĢазмеÑĢ
    0.10
    ä»·åĢ¼
    0.10
    valueOf
    0.10
     value
    0.10
    ãĤµãĤ¤ãĤº
    0.09
    尺寸
    0.09
    éĩįéĩı
    0.09
    æĭį
    0.09
    value
    0.09
    Activations Density 0.091%

    No Known Activations