© 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. 21414
    Prev
    Next
    INDEX
    Explanations

    programming and parsing

    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
    ergestellt
    -0.10
    HING
    -0.09
    sWith
    -0.09
    enje
    -0.09
    gether
    -0.09
    Ñģие
    -0.09
    ierzch
    -0.09
    phans
    -0.09
    ernals
    -0.08
    ityEngine
    -0.08
    POSITIVE LOGITS
    âĢij
    0.09
    ist
    0.08
    âĢIJ
    0.08
    -
    0.08
    åĽ¢æĪIJåijĺ
    0.07
    çĺ¤
    0.07
    ium
    0.07
    -of
    0.07
    -d
    0.07
    ÑĦ
    0.07
    Activations Density 2.890%

    No Known Activations