© 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. 18847
    Prev
    Next
    INDEX
    Explanations

    list items ending with punctuation

    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
    .TryParse
    -0.07
     ìĭ±ê¸Ģ
    -0.06
    amburger
    -0.06
    ettem
    -0.06
    allet
    -0.06
     Jug
    -0.06
    çıĬ
    -0.06
    å½ĵæľŁ
    -0.06
    /el
    -0.06
    amb
    -0.06
    POSITIVE LOGITS
     ë°ĺë©´
    0.12
    ';
    0.11
     whereas
    0.11
    »;
    0.11
    ï¼Ľ
    0.10
    ";
    0.10
    ”;
    0.10
    ãĢįãĢģ
    0.10
    **;
    0.10
    `;
    0.10
    Activations Density 0.479%

    No Known Activations