© 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. 24634
    Prev
    Next
    INDEX
    Explanations

    proposals or estimates

    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
    åĽ½åįİ
    -0.07
    ÑĮе
    -0.07
    aho
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    æĪĸå¤ļ
    -0.07
     hum
    -0.07
    zeg
    -0.07
    aksin
    -0.07
    addock
    -0.07
    ä¸ĢéĢļ
    -0.07
    POSITIVE LOGITS
    oked
    0.08
    licherweise
    0.07
    avoir
    0.07
    imeo
    0.07
    ä¸įçĶŁ
    0.07
    å·²ä¹ħ
    0.07
    odel
    0.07
    ult
    0.07
    å·²ä¹ħçļĦ
    0.07
    loit
    0.06
    Activations Density 0.058%

    No Known Activations