© 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. 42668
    Prev
    Next
    INDEX
    Explanations

    remove invalid characters

    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
    Ùĩد
    -0.08
    è¿ĺæľª
    -0.07
    _abort
    -0.07
    bal
    -0.07
    (fabs
    -0.07
    доваÑĤÑĮ
    -0.07
    _dispatch
    -0.07
    бал
    -0.07
     mạ
    -0.07
     BOTH
    -0.07
    POSITIVE LOGITS
    åİ»éĻ¤
    0.09
     remove
    0.08
     removing
    0.08
     unn
    0.08
    åİ»æİī
    0.07
    TextInput
    0.07
     menghilangkan
    0.07
     concaten
    0.07
     extracting
    0.07
    å¹²åĩĢ
    0.07
    Activations Density 0.036%

    No Known Activations