© 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. 62191
    Prev
    Next
    INDEX
    Explanations

    horse history

    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
    åī
    -0.07
    redo
    -0.06
    eki
    -0.06
    uret
    -0.06
     mak
    -0.06
    atto
    -0.06
    hoa
    -0.06
     Rup
    -0.06
    éļ¾æĺĵ
    -0.06
    anda
    -0.06
    POSITIVE LOGITS
    пиÑĤ
    0.08
    shint
    0.08
     izle
    0.07
    пил
    0.07
    unger
    0.07
    åĽ±
    0.07
    hyl
    0.07
    snippet
    0.07
    ahir
    0.07
     strokeLine
    0.07
    Activations Density 0.184%

    No Known Activations