© 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. 39148
    Prev
    Next
    INDEX
    Explanations

    birth year horoscopes

    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
    urb
    -0.07
    å¾Ĺä¸į
    -0.07
    ä»İ严
    -0.07
    iw
    -0.07
    omp
    -0.06
    æĶ«
    -0.06
    ãģ·
    -0.06
    ëŁ½
    -0.06
    åݦ
    -0.06
    pons
    -0.06
    POSITIVE LOGITS
    åij¨æľŁçļĦ
    0.09
    åĨľåİĨ
    0.08
    metis
    0.08
    horn
    0.08
     lunar
    0.08
    [++
    0.07
    ahead
    0.07
    меÑĤи
    0.07
    astro
    0.07
    _POINTER
    0.07
    Activations Density 0.004%

    No Known Activations