© 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. 9959
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

    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
    idou
    -0.08
    åĨ°åĨ»
    -0.08
    ateg
    -0.07
    ovu
    -0.07
     дейÑģÑĤв
    -0.07
     Fully
    -0.07
    ény
    -0.07
    iniu
    -0.07
    tuk
    -0.07
     fully
    -0.06
    POSITIVE LOGITS
    $$$
    0.07
    ieb
    0.07
    /title
    0.06
    bum
    0.06
    çīĪåĿĹ
    0.06
     exclusion
    0.06
    ÃŃst
    0.06
    å°½ãģı
    0.06
    redd
    0.06
    Wunused
    0.06
    Activations Density 0.007%

    No Known Activations