© 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. 62831
    Prev
    Next
    INDEX
    Explanations

    casual and relaxed environments

    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
    åı¯è°ĵ
    -0.10
     оÑģ
    -0.09
    寸
    -0.09
    stin
    -0.08
    -visible
    -0.08
    åĽºåĮĸ
    -0.08
    ä¸ĭ游
    -0.08
    éĴ±åĮħ
    -0.08
    ì°¬
    -0.08
    ATAB
    -0.08
    POSITIVE LOGITS
    亲åĪĩ
    0.14
    è½»æĿ¾
    0.12
     relaxed
    0.12
    æĶ¾æĿ¾
    0.11
    å¼ĢæĶ¾å¼ı
    0.11
    æīĵçł´äºĨ
    0.10
    èĢĮä¸įæĺ¯
    0.10
    æĶ¾å®½
    0.10
    亲
    0.10
    æĿ¾
    0.10
    Activations Density 0.026%

    No Known Activations