© 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. 40085
    Prev
    Next
    INDEX
    Explanations

    52-week lows

    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
    !!:
    -0.07
    åħĭç¦ı
    -0.07
    æľĪæľĪ
    -0.07
    βο
    -0.07
    Ø®ÙĬ
    -0.07
    aub
    -0.07
     circular
    -0.07
     замеÑģÑĤ
    -0.07
    Subsystem
    -0.07
    ysh
    -0.07
    POSITIVE LOGITS
    ÙĦات
    0.07
    å¹´ç»Ī
    0.07
    trinsic
    0.07
     пÑĢиÑĩ
    0.07
    çĦ¶åIJİå°±
    0.07
    िता
    0.07
    对åħ¶è¿Ľè¡Į
    0.06
    å¹´å°Ĩ
    0.06
     nun
    0.06
    å°Ĩå®ĥ们
    0.06
    Activations Density 0.002%

    No Known Activations