© 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. 43749
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and symbols

    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
    è£ħæľº
    -0.07
    æ±Ģ
    -0.07
    äºĮ代
    -0.07
    áĢ·áĢº
    -0.07
    pline
    -0.07
    æļ§
    -0.07
    å®Īæ³ķ
    -0.07
     Flake
    -0.07
     Lump
    -0.07
    ston
    -0.07
    POSITIVE LOGITS
    å°º
    0.08
    æĿ¨æŁ³
    0.07
     Erick
    0.07
    h
    0.07
    ringe
    0.06
    hor
    0.06
     sire
    0.06
    æ³Į
    0.06
    rig
    0.06
    åīįè¿Ľ
    0.06
    Activations Density 0.011%

    No Known Activations