© 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. 28510
    Prev
    Next
    INDEX
    Explanations

    correction

    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
    erness
    -0.10
    hood
    -0.08
    ÙĥرÙĬ
    -0.08
    keit
    -0.08
    å¿ĺè¿Ķ
    -0.08
    rene
    -0.08
     liá»ħu
    -0.07
    ÏĥÏĩ
    -0.07
    ettor
    -0.07
    olean
    -0.07
    POSITIVE LOGITS
    /add
    0.10
    ive
    0.09
    ìĤ¬íķŃ
    0.08
     ìĤ¬íķŃ
    0.08
    ate
    0.08
    naire
    0.08
    /ref
    0.08
     apport
    0.08
    amenta
    0.08
    aries
    0.07
    Activations Density 0.017%

    No Known Activations