© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    App, Anna, Intervenor

    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
    ocat
    -0.07
    è³ij
    -0.07
    mix
    -0.06
    æIJħæĭĮåĿĩåĮĢ
    -0.06
    åīį车
    -0.06
    emies
    -0.06
     inherent
    -0.06
    erty
    -0.06
    æ³Ľæ»¥
    -0.06
    åľ¨å¿ħ
    -0.06
    POSITIVE LOGITS
    cente
    0.08
    èĪŀ
    0.08
    饮
    0.07
    ustos
    0.07
    OUSE
    0.07
    -sync
    0.07
    vÄĽ
    0.07
    áŀ¶áŀĻ
    0.07
    çŁ³åĪ»
    0.07
    fdb
    0.07
    Activations Density 0.002%

    No Known Activations