© 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. 15403
    Prev
    Next
    INDEX
    Explanations

    self / actual

    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
     Zion
    -0.07
    HECK
    -0.07
    CHAN
    -0.07
    ieÃŁen
    -0.07
    AFX
    -0.07
    æĸĻåĪ°
    -0.07
    orris
    -0.07
    ECK
    -0.07
    å³¥
    -0.07
    otis
    -0.06
    POSITIVE LOGITS
    æľ¬èº«å°±æĺ¯
    0.10
    亲身ä½ĵéªĮ
    0.09
    å®ŁéļĽãģ«
    0.09
    å®ŀéĻħæĵįä½ľ
    0.09
     itself
    0.09
    æľ¬èº«
    0.08
    å®ŀéĻħ
    0.08
     actual
    0.08
    actual
    0.08
     Actual
    0.08
    Activations Density 1.051%

    No Known Activations