© 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. 29534
    Prev
    Next
    INDEX
    Explanations

    physician, robbery, electronically, Colombia, Robinson, forecasts, Sykes, celebrations, laboratories, satellite

    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
    semblée
    -0.08
    ¬ģ
    -0.08
    ught
    -0.08
    <tool_response>
    -0.07
    azzi
    -0.07
    ials
    -0.07
    дова
    -0.07
    Âł
    -0.07
    ensity
    -0.07
    uern
    -0.07
    POSITIVE LOGITS
    adays
    0.20
    etheless
    0.20
    gether
    0.17
    èĩªå·±
    0.15
    ostante
    0.15
    odore
    0.14
    bsites
    0.14
    quoi
    0.13
    efois
    0.12
    empre
    0.12
    Activations Density 0.189%

    No Known Activations