© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16382
    Prev
    Next
    INDEX
    Explanations

    thank you / thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĥŃéŨ
    -0.06
    igli
    -0.06
    è®°èĢħåľ¨
    -0.06
    è¶ĭ
    -0.06
    便
    -0.06
    åĬ¿åľ¨å¿ħ
    -0.06
    带æľī
    -0.06
    æį®æѤ
    -0.06
     orth
    -0.05
    èĩªçĶ¨
    -0.05
    POSITIVE LOGITS
     заÑģл
    0.11
    çļĦæĶ¯æĮģ
    0.10
    çļĦè´¡çĮ®
    0.10
    èĩªå·±çļĦåĬªåĬĽ
    0.09
     contributo
    0.09
     contributions
    0.09
    èĩ´è°¢
    0.09
    ãģ®ãģĬãģĭãģĴ
    0.08
    æľīåĬł
    0.08
     contributors
    0.08
    Activations Density 0.321%

    No Known Activations