© 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. 24391
    Prev
    Next
    INDEX
    Explanations

    improper integrals or names

    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
    xffff
    -0.08
     overe
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    terra
    -0.07
    cium
    -0.07
    å±¥
    -0.07
    åīįè¨Ģ
    -0.07
    åįģç«ł
    -0.07
    æĺ¯ä¸Ģå¥Ĺ
    -0.07
    orea
    -0.07
    POSITIVE LOGITS
     squared
    0.07
     asympt
    0.07
    ä¸ĭè½½å®īè£ħ
    0.07
     density
    0.07
    wit
    0.06
     sing
    0.06
    äºĮç±»
    0.06
    èĢĮæŃ»
    0.06
     decay
    0.06
     integr
    0.06
    Activations Density 0.007%

    No Known Activations