© 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. 26210
    Prev
    Next
    INDEX
    Explanations

    other hand

    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
    èľ¡
    -0.07
    æīij
    -0.07
    èħĬ
    -0.07
    æľ´
    -0.06
    jee
    -0.06
    åħ½
    -0.06
    è¢ħ
    -0.06
    Ñħов
    -0.06
    åIJĪæ³ķçļĦ
    -0.06
    æľīåºıçļĦ
    -0.06
    POSITIVE LOGITS
    dsm
    0.09
    ä¸Ģ缮
    0.08
    ToStr
    0.08
     estrang
    0.08
    诣
    0.08
    हà¥Ģà¤Ĥ
    0.08
    edd
    0.08
    çļĦç½ijç«Ļ
    0.08
    ä¹ĥ
    0.08
    袱
    0.07
    Activations Density 0.816%

    No Known Activations