© 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. 57318
    Prev
    Next
    INDEX
    Explanations

    related generally

    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
    ricia
    -0.08
    ])**
    -0.08
    ä»ij
    -0.07
    ÙħÙĬØ©
    -0.07
    eriop
    -0.07
    ]-$
    -0.07
    é¦ĸ个
    -0.07
    ÈĽe
    -0.07
    -runner
    -0.07
    avras
    -0.07
    POSITIVE LOGITS
    zilla
    0.07
    ×ķ×ķ
    0.07
     Whilst
    0.06
     anale
    0.06
     whilst
    0.06
     somebody
    0.06
     anybody
    0.06
     proviso
    0.06
    .codes
    0.06
    Ã¤ÃŁ
    0.06
    Activations Density 0.689%

    No Known Activations