© 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. 29650
    Prev
    Next
    INDEX
    Explanations

    expressing need or ability

    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
    isode
    -0.08
    帮åĬ©ä»ĸ们
    -0.08
    tml
    -0.08
    \Unit
    -0.08
    sius
    -0.08
    линг
    -0.08
    è§ģä»ĸ
    -0.08
    chner
    -0.08
    OLON
    -0.08
    ombo
    -0.08
    POSITIVE LOGITS
    èĤĨ
    0.07
    iw
    0.07
    ucch
    0.07
    0.06
    ry
    0.06
    ë´ī
    0.06
    obel
    0.06
    Ñĥк
    0.06
    æĻļè¾Ī
    0.06
    æĸ°
    0.06
    Activations Density 0.067%

    No Known Activations