© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10792
    Prev
    Next
    INDEX
    Explanations

    link and with his

    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
    ä¸įåıª
    -0.08
    ãģłãģijãģ§ãģ¯ãģªãģı
    -0.07
    кове
    -0.07
    otis
    -0.07
    odyn
    -0.07
    iage
    -0.07
    ozy
    -0.07
    å°Ķ夫
    -0.07
     mình
    -0.07
    ãģłãģijãģ§ãģªãģı
    -0.07
    POSITIVE LOGITS
     actual
    0.10
    å®ŀéĻħçļĦ
    0.10
     eventual
    0.09
    å®ĥä»¬åľ¨
    0.09
    å®ŀéĻħ
    0.08
    å®ŁéļĽãģ®
    0.08
    actual
    0.08
    å®ŀéĻħéľĢè¦ģ
    0.08
     potential
    0.07
     its
    0.07
    Activations Density 0.082%

    No Known Activations