© 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. 39717
    Prev
    Next
    INDEX
    Explanations

    texture and patterns

    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
    éĴĹ
    -0.10
    orda
    -0.10
    éĵ§
    -0.10
    åĶ¢
    -0.09
    æī¬
    -0.09
    äºıæįŁ
    -0.09
    åį¡éĢļ
    -0.09
    оÑģÑĤи
    -0.09
    满æĢĢ
    -0.09
    åľºåIJĪ
    -0.09
    POSITIVE LOGITS
    纹çIJĨ
    0.15
     patterns
    0.15
     pattern
    0.15
     Patterns
    0.14
    _pattern
    0.14
    纹
    0.14
    pattern
    0.14
     texture
    0.13
    èĬ±çº¹
    0.13
     Pattern
    0.13
    Activations Density 0.136%

    No Known Activations