© 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. 32489
    Prev
    Next
    INDEX
    Explanations

    C to VB.NET or court appeals

    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
    hausen
    -0.08
    icas
    -0.07
    èĤ²
    -0.07
    bay
    -0.07
    _legend
    -0.07
    otto
    -0.07
    schap
    -0.06
    illing
    -0.06
    quisition
    -0.06
    ↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    erton
    0.08
    niec
    0.07
    amer
    0.07
    estet
    0.07
    earn
    0.07
    ory
    0.07
    athi
    0.07
    ovah
    0.06
    å°¿é¢ij
    0.06
    ظر
    0.06
    Activations Density 0.001%

    No Known Activations