© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2085
    Prev
    Next
    INDEX
    Explanations

    ending or stopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    inos
    -0.26
     intern
    -0.24
    缦
    -0.23
    å¼
    -0.23
    磫
    -0.23
    æĹ¢åı¯ä»¥
    -0.23
    _SPE
    -0.22
    çŀĦåĩĨ
    -0.22
     dens
    -0.21
    Caught
    -0.21
    POSITIVE LOGITS
    (exit
    0.30
     exit
    0.30
    éĢĢåĩº
    0.30
     prematurely
    0.29
     exits
    0.28
     unfinished
    0.28
    ç»ĪæŃ¢
    0.28
     immediately
    0.28
     Exit
    0.27
     sỼm
    0.27
    Activations Density 0.054%

    No Known Activations