© 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. 4383
    Prev
    Next
    INDEX
    Explanations

    http and url schemas

    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
    ecto
    -0.07
    ched
    -0.06
    ĥ
    -0.06
    åĨįæİ¥
    -0.06
    ect
    -0.06
    ľ
    -0.06
     Briggs
    -0.06
    teri
    -0.06
    é¡Ķ
    -0.06
    ä¸įè¾¾
    -0.06
    POSITIVE LOGITS
    eggio
    0.08
    ertian
    0.07
    大åħ¸
    0.07
    Spell
    0.07
    çŁ¥è¯Ĩç«ŀèµĽ
    0.07
    สล
    0.07
    GenericType
    0.07
    TargetException
    0.07
    inato
    0.07
    <|quad_start|>
    0.07
    Activations Density 0.011%

    No Known Activations