© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14047
    Prev
    Next
    INDEX
    Explanations

    waiting for time to pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    常年
    -0.27
    zyst
    -0.22
    å¯Ħæīĺ
    -0.22
    æ¯ıå¹´
    -0.21
    ä¸Ģå¹´
    -0.21
    éķ¿æľŁ
    -0.20
    éĢIJå¹´
    -0.20
    æħ¨
    -0.20
     Dates
    -0.20
     Springer
    -0.20
    POSITIVE LOGITS
     seconds
    0.31
     minutes
    0.30
     вÑĢемени
    0.29
    seconds
    0.27
    è¿ĩåIJİ
    0.27
     time
    0.26
     interval
    0.26
    minutes
    0.26
    åĩłåĪĨéĴŁ
    0.25
    ä¸ĢåĪĨéĴŁ
    0.25
    Activations Density 0.141%

    No Known Activations