© 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. 2062
    Prev
    Next
    INDEX
    Explanations

    metadata and related information

    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
    顺
    -0.09
    ä¸ĵ享
    -0.08
     slit
    -0.08
     ÑĦин
    -0.08
     tol
    -0.08
    ä¸įåħ¬å¹³
    -0.08
     Tess
    -0.08
    å¾Ĵ
    -0.08
    æĴŃæĬ¥
    -0.08
    สà¸ļาย
    -0.08
    POSITIVE LOGITS
     metadata
    0.17
    metadata
    0.15
    (metadata
    0.14
     Metadata
    0.13
    Metadata
    0.13
    _metadata
    0.13
    åħĥ
    0.12
     meta
    0.12
    MetaData
    0.12
    _METADATA
    0.12
    Activations Density 0.303%

    No Known Activations