© 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. 56327
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    ç½ij讯
    -0.08
    unami
    -0.08
    hood
    -0.08
    uai
    -0.07
     either
    -0.07
    idencia
    -0.07
     Ñħода
    -0.07
    alismo
    -0.07
    erno
    -0.07
    ement
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.08
    erce
    0.07
    Ĥ
    0.07
    Ĭ
    0.07
    ãģĬèħ¹
    0.06
    à¹Į
    0.06
    amil
    0.06
    _COND
    0.06
    s
    0.06
    re
    0.06
    Activations Density 0.001%

    No Known Activations