© 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. 41390
    Prev
    Next
    INDEX
    Explanations

    adjusted or controlling for

    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
    <|box_end|>
    -0.08
    æĪŁ
    -0.08
    ymoon
    -0.08
    ienst
    -0.07
    ocy
    -0.07
    odes
    -0.07
    osit
    -0.07
    sst
    -0.07
    illet
    -0.07
    ilet
    -0.07
    POSITIVE LOGITS
    (background
    0.09
    èĥĮæĻ¯
    0.08
    .background
    0.08
    ä»ĩ
    0.08
    background
    0.08
    /background
    0.08
     background
    0.08
    Background
    0.07
    ivariate
    0.07
     backgrounds
    0.07
    Activations Density 0.036%

    No Known Activations