© 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. 64615
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    è¦ģä¸į
    -0.07
    aldi
    -0.07
    onger
    -0.07
    ä¼´
    -0.07
    æĥŃ
    -0.07
    _eof
    -0.06
    wich
    -0.06
    omet
    -0.06
    wi
    -0.06
    é¹ħ
    -0.06
    POSITIVE LOGITS
    inois
    0.08
    社
    0.07
    á»įa
    0.07
    éĩijçİī
    0.07
    áĥĿáĥĵ
    0.07
    "]="
    0.07
    TRACK
    0.07
    使å®ĥ
    0.07
    ointment
    0.07
    ntag
    0.07
    Activations Density 0.011%

    No Known Activations