© 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. 51198
    Prev
    Next
    INDEX
    Explanations

    no need or requirement

    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
    ä¸įæĮī
    -0.08
    onna
    -0.07
     pursuant
    -0.06
     Serious
    -0.06
    unal
    -0.06
    mares
    -0.06
    VERR
    -0.06
    naf
    -0.06
    annot
    -0.06
    ached
    -0.06
    POSITIVE LOGITS
     hoeft
    0.09
     worry
    0.09
    æĵĶå¿ĥ
    0.09
     needing
    0.09
     messy
    0.08
     unnecessary
    0.08
     ë³µìŀ¡íķľ
    0.08
     complicated
    0.08
     reliance
    0.08
     worrying
    0.08
    Activations Density 0.104%

    No Known Activations