© 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. 31157
    Prev
    Next
    INDEX
    Explanations

    Lei, interesting numbers, live

    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
     Demonstr
    -0.07
    Demon
    -0.07
     verbally
    -0.06
    HX
    -0.06
    ire
    -0.06
     '
    -0.06
    vs
    -0.06
    èį¯æĪ¿
    -0.06
    éĩijåĪļ
    -0.06
    ka
    -0.06
    POSITIVE LOGITS
    ongyang
    0.08
    å°ıé¢ĺ
    0.08
    asher
    0.08
    äumt
    0.08
    \uff
    0.07
     nén
    0.07
    æľīåħ³æ³ķå¾ĭ
    0.07
     Certa
    0.07
    ovil
    0.07
    REATE
    0.07
    Activations Density 0.065%

    No Known Activations