© 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. 57883
    Prev
    Next
    INDEX
    Explanations

    classified as

    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
    çŀ»
    -0.08
    è
    -0.07
    iggins
    -0.07
    ynamo
    -0.07
    æ³¾
    -0.07
    باع
    -0.07
    usada
    -0.07
    presa
    -0.07
    é¥
    -0.07
    æŁıæŀĹ
    -0.07
    POSITIVE LOGITS
    _AUX
    0.08
    çIJĨ论水平
    0.08
    åıĬ产åĵģ
    0.07
    kasten
    0.07
    upi
    0.07
    'o
    0.07
    ffit
    0.07
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.06
     curse
    0.06
    æĵĭ
    0.06
    Activations Density 0.013%

    No Known Activations