© 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. 16559
    Prev
    Next
    INDEX
    Explanations

    container/contents

    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
    æºī
    -0.08
    éĩĮéĿ¢æľī
    -0.08
    ubits
    -0.07
    åłªç§°
    -0.07
    uille
    -0.07
    æĥ³åľ¨
    -0.07
    !(
    -0.07
    æįķ
    -0.07
    ntl
    -0.06
    ä¸ºåŁºç¡ĢçļĦ
    -0.06
    POSITIVE LOGITS
    hurst
    0.09
    åĢĻéĢī
    0.07
    æīĢéľĢ
    0.07
    æīĢéľĢçļĦ
    0.07
    ocas
    0.07
    óx
    0.06
     candidate
    0.06
    ä¾Ŀ
    0.06
    ä»İæѤ
    0.06
    ä¸įè¾ŀ
    0.06
    Activations Density 0.086%

    No Known Activations