© 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. 63602
    Prev
    Next
    INDEX
    Explanations

    fellow members and colleagues

    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
    erweise
    -0.10
    imal
    -0.08
    ãģµãģĨãģ«
    -0.08
     ëĮĢë¡ľ
    -0.08
    ÌĢ
    -0.08
    вне
    -0.08
    só
    -0.07
    群ä¼ĹåĬŀå®ŀäºĭ
    -0.07
    ically
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    POSITIVE LOGITS
    -sama
    0.10
    ings
    0.09
    åħ¶äºĭ
    0.08
    ships
    0.08
    ievo
    0.08
    nees
    0.07
    ools
    0.07
    ÙħØ©
    0.07
    lasses
    0.07
     nhau
    0.06
    Activations Density 0.007%

    No Known Activations