© 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. 19544
    Prev
    Next
    INDEX
    Explanations

    unnecessary treatment or procedures

    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
    ickle
    -0.08
    osate
    -0.08
     abused
    -0.07
    åıĪå¿«
    -0.07
    ä»»ä½ķä¸Ģ个
    -0.07
    çŁ¥è¶³
    -0.07
     naturally
    -0.07
     koronav
    -0.07
    zion
    -0.07
     fracas
    -0.07
    POSITIVE LOGITS
    缸åºĶçļĦ
    0.09
    é¢Ŀå¤ĸçļĦ
    0.09
     additional
    0.08
     berupa
    0.08
    é¢Ŀå¤ĸ
    0.07
     extra
    0.07
     ì¶Ķê°Ģ
    0.07
    缸åºĶ
    0.07
    çļĦæݪæĸ½
    0.07
    追åĬł
    0.07
    Activations Density 0.456%

    No Known Activations