© 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. 13745
    Prev
    Next
    INDEX
    Explanations

    please do not

    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
     ze
    -0.07
    oor
    -0.06
     ready
    -0.06
    äºĭä¸Ń
    -0.06
     :)
    -0.06
     moo
    -0.06
    var
    -0.06
    æĹłè®ºä»İ
    -0.06
    orent
    -0.06
    å©ķ
    -0.06
    POSITIVE LOGITS
    å¿ħé¡»æľī
    0.15
    å¿ħé¡»è¦ģæľī
    0.13
    å¿ħé¡»
    0.13
    Must
    0.13
    æŶå¿ħé¡»
    0.13
     Must
    0.12
    å°±å¿ħé¡»
    0.12
    å¿ħé¡»åľ¨
    0.12
    å¿ħé¡»æĺ¯
    0.12
    å¿ħé¡»è¦ģ
    0.12
    Activations Density 0.085%

    No Known Activations