© 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. 25205
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols like $

    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
    atest
    -0.08
    çģµå±±
    -0.08
    eel
    -0.08
    erti
    -0.08
    orts
    -0.07
    erve
    -0.07
    _dicts
    -0.07
    èĢĮ论
    -0.07
    rement
    -0.07
    TML
    -0.07
    POSITIVE LOGITS
    ä¾Ī
    0.07
    chetta
    0.07
    æĴ¬
    0.07
    راÙĤ
    0.07
    araf
    0.06
    .OS
    0.06
    å¼ķ以为
    0.06
    çĤĻ
    0.06
    '.
    0.06
     då
    0.06
    Activations Density 0.069%

    No Known Activations