© 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. 20194
    Prev
    Next
    INDEX
    Explanations

    plus signs and parentheses

    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
    haupt
    -0.10
    áĢ¸
    -0.10
    jenigen
    -0.09
    zelf
    -0.09
    heden
    -0.09
    ãĥ³ãĤ¸
    -0.08
    andez
    -0.08
    ĺ
    -0.08
     appunto
    -0.08
     punta
    -0.08
    POSITIVE LOGITS
    datable
    0.10
    itive
    0.10
    erior
    0.09
    dater
    0.08
    ython
    0.08
    enticated
    0.08
    /-
    0.08
    ivity
    0.08
    ãģ£ãģ±
    0.08
    /down
    0.08
    Activations Density 0.066%

    No Known Activations