© 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. 9803
    Prev
    Next
    INDEX
    Explanations

    overtime hours

    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
    屯
    -0.09
    ullet
    -0.09
    çªĺ
    -0.09
    缴å¾Ħ
    -0.09
    å½ĵæŶ
    -0.09
    ä¸īåĽĽ
    -0.08
    éļĶçĿĢ
    -0.08
     Decay
    -0.08
    ä¸Ģè·¯ä¸Ĭ
    -0.08
    åĨ³å¿ĥ
    -0.08
    POSITIVE LOGITS
    åĬłçıŃ
    0.18
     overtime
    0.13
     hours
    0.12
    hours
    0.11
    ä¼ijæģ¯
    0.10
    æĬ¥éħ¬
    0.10
    _hours
    0.10
    æīĵåį¡
    0.10
    åĥį
    0.10
    å²Ĺä½į
    0.10
    Activations Density 0.068%

    No Known Activations