© 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. 60879
    Prev
    Next
    INDEX
    Explanations

    dotted numbers

    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
    edly
    -0.09
    Ïĥια
    -0.07
    zinho
    -0.07
    ijin
    -0.07
    idin
    -0.07
    æīįè¡Į
    -0.06
    ihu
    -0.06
    .players
    -0.06
    cide
    -0.06
    á»ıng
    -0.06
    POSITIVE LOGITS
    accep
    0.07
    è¨Ģä¹ĭ
    0.07
    íķ´ì§Ħ
    0.06
    _guard
    0.06
    ллÑı
    0.06
    colar
    0.06
    MOTE
    0.06
    ulls
    0.06
    ായ
    0.06
    rib
    0.06
    Activations Density 0.007%

    No Known Activations