© 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. 49535
    Prev
    Next
    INDEX
    Explanations

    Mat, NBC, Nat, Unity, Little, U, merit

    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
    åħ¶å®ĥåªĴä½ĵ
    -0.09
    åĴĮæĶ¯æĮģ
    -0.08
    boli
    -0.08
    ographique
    -0.08
    à¸ķัว
    -0.07
    gge
    -0.07
    wares
    -0.07
    Playback
    -0.07
    身ä¸Ĭä¸ĭ
    -0.07
    sza
    -0.07
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.08
    å¸ģ
    0.08
    ç¬Ķä¸ĭçļĦ
    0.07
    -style
    0.07
    çīĪçļĦ
    0.07
    elman
    0.07
    å¹£
    0.07
    .com
    0.06
    -owned
    0.06
    jc
    0.06
    Activations Density 0.370%

    No Known Activations