© 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. 61043
    Prev
    Next
    INDEX
    Explanations

    more ... than

    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
    istra
    -0.08
     lepas
    -0.07
    kan
    -0.07
    éĵ¿
    -0.07
    oura
    -0.06
    æīĢ以è¦ģ
    -0.06
     gist
    -0.06
    bower
    -0.06
     Arche
    -0.06
     Celsius
    -0.06
    POSITIVE LOGITS
     surprisingly
    0.09
    æĥ³è±¡ä¸Ń
    0.09
    è¶ħä¹İ
    0.09
    æ¯ĶæĪij们
    0.09
     unexpectedly
    0.09
     unexpected
    0.09
    ä¹į
    0.08
     underestimated
    0.08
    Unexpected
    0.08
    å®Łãģ¯
    0.08
    Activations Density 0.251%

    No Known Activations