© 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. 47145
    Prev
    Next
    INDEX
    Explanations

    r or right

    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
    å°Ķæĸ¯
    -0.07
    åħ¨éĿ¢å®ŀæĸ½
    -0.07
    å®Ĺ
    -0.06
    ewa
    -0.06
    uche
    -0.06
    ikor
    -0.06
    .position
    -0.06
     Trout
    -0.06
    çĴ§
    -0.06
    orry
    -0.06
    POSITIVE LOGITS
    ãģĦãģļãĤĮ
    0.09
     whichever
    0.08
    è¿ĻäºĽåľ°æĸ¹
    0.07
    ãi
    0.07
    ,function
    0.07
    æĮĿ
    0.07
    ängen
    0.07
    åľ¨æīĢ
    0.07
    tores
    0.07
     fras
    0.07
    Activations Density 0.339%

    No Known Activations