© 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. 60615
    Prev
    Next
    INDEX
    Explanations

    log Mar visual acuity

    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
    æ±ł
    -0.08
    UME
    -0.07
     restless
    -0.07
    zeb
    -0.06
    å¤ķ
    -0.06
    çĽ¸å¯¹è¾ĥé«ĺ
    -0.06
    _mgr
    -0.06
    ilan
    -0.06
    izo
    -0.06
    til
    -0.06
    POSITIVE LOGITS
     instead
    0.08
    azon
    0.08
    iad
    0.08
     bada
    0.07
     statt
    0.07
     beis
    0.07
    -bot
    0.07
     lur
    0.07
    èĢĮä¸įæĺ¯
    0.07
    instead
    0.07
    Activations Density 0.006%

    No Known Activations