© 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. 8193
    Prev
    Next
    INDEX
    Explanations

    date titles

    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
    éĹĨ
    -0.08
    adx
    -0.08
    adge
    -0.08
    quo
    -0.08
    è¿Ľä¸ĢæŃ¥çļĦ
    -0.08
    achter
    -0.08
    Evt
    -0.07
    elyn
    -0.07
    人æ°ijéĻªå®¡åijĺ
    -0.07
    aih
    -0.07
    POSITIVE LOGITS
    ross
    0.08
    onos
    0.08
    rodu
    0.07
    ä½ĻåĬĽ
    0.07
     cape
    0.07
     ross
    0.06
    dek
    0.06
    ROSS
    0.06
     synthes
    0.06
     merch
    0.06
    Activations Density 0.016%

    No Known Activations