© 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. 20980
    Prev
    Next
    INDEX
    Explanations

    read more

    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
    оÑĢод
    -0.08
    arella
    -0.08
    illon
    -0.07
    isms
    -0.07
    phans
    -0.07
    онÑĭ
    -0.07
    ä½ķåľ°
    -0.07
    äºĶèĬ±
    -0.07
    ä¸ŃéĹ´
    -0.07
     Played
    -0.07
    POSITIVE LOGITS
    aju
    0.07
    çī¹å°Ķ
    0.07
     Improvement
    0.07
    缴
    0.07
    _MAJOR
    0.06
    粪便
    0.06
    à®±à¯įப
    0.06
    Wnd
    0.06
    ehr
    0.06
     Roos
    0.06
    Activations Density 0.002%

    No Known Activations