© 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. 45952
    Prev
    Next
    INDEX
    Explanations

    scaling behavior, approach, principle, functions

    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
    ationToken
    -0.08
    HING
    -0.08
    untime
    -0.08
    chaft
    -0.08
    ÙĤص
    -0.08
    OUCH
    -0.08
    LY
    -0.08
    eger
    -0.07
    Ø«ÙĨ
    -0.07
    ctor
    -0.07
    POSITIVE LOGITS
    weise
    0.07
    å¾Ĺå½ĵ
    0.07
    rh
    0.07
    æĢ§åľ°
    0.07
    uar
    0.07
    enario
    0.07
    cial
    0.06
    èĩªå¦Ĥ
    0.06
    irk
    0.06
     ngầm
    0.06
    Activations Density 0.006%

    No Known Activations