© 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. 18269
    Prev
    Next
    INDEX
    Explanations

    all-on-4 or four-piece

    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
    ×ķק
    -0.07
    ursal
    -0.07
    -widgets
    -0.07
    wed
    -0.07
     dom
    -0.07
    osal
    -0.07
    对åħļ
    -0.07
    å®īåħ¨çŁ¥è¯Ĩ
    -0.06
    _DOM
    -0.06
     Burgess
    -0.06
    POSITIVE LOGITS
    ä»Ĭå¹´
    0.07
    swick
    0.07
    appen
    0.07
    dition
    0.07
    _COMPLEX
    0.06
    atera
    0.06
    lore
    0.06
    chutz
    0.06
    áĥĶáĥĵ
    0.06
    ktop
    0.06
    Activations Density 0.012%

    No Known Activations