© 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. 58159
    Prev
    Next
    INDEX
    Explanations

    rounding numbers to decimal places

    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
    çŀ§
    -0.08
    -runner
    -0.07
    çİ®
    -0.07
    _Enter
    -0.07
    allen
    -0.06
     solos
    -0.06
    ĥ
    -0.06
    QUIRE
    -0.06
    .enter
    -0.06
     slash
    -0.06
    POSITIVE LOGITS
    otre
    0.09
    haps
    0.08
    extr
    0.07
    ×ł×¡
    0.07
    retta
    0.07
    abal
    0.07
    erie
    0.06
    è¦Ĩ
    0.06
    ains
    0.06
    -extra
    0.06
    Activations Density 0.004%

    No Known Activations