© 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. 11594
    Prev
    Next
    INDEX
    Explanations

    powerful

    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
    lotte
    -0.21
    大åĬĽåıijå±ķ
    -0.20
    razil
    -0.18
    åħ¨éĿ¢åıijå±ķ
    -0.18
    coe
    -0.18
    uro
    -0.18
    çݰ象
    -0.17
     nhạc
    -0.17
    íĭ±
    -0.17
    ledon
    -0.17
    POSITIVE LOGITS
    åĬŁçİĩ
    0.29
    /power
    0.28
    power
    0.28
     power
    0.25
    强大çļĦ
    0.25
    ä¸įæĸŃå¢ŀ强
    0.25
    (power
    0.25
    åĬĽéĩı
    0.25
     моÑī
    0.24
    -power
    0.23
    Activations Density 0.065%

    No Known Activations