© 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. 42389
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
    -meta
    -0.07
     Ingl
    -0.07
    åİ»çļ®
    -0.07
     syntax
    -0.06
    å¤Ħå¤Ħéķ¿
    -0.06
    yntax
    -0.06
    /module
    -0.06
    롤
    -0.06
    UNG
    -0.06
    ä¸Ģ个éĩįè¦ģ
    -0.06
    POSITIVE LOGITS
    hone
    0.08
    éħįç½®çļĦ
    0.07
    ’h
    0.07
    alive
    0.07
     Lemma
    0.07
    uco
    0.07
    вÑĤоÑĢÑĭÑħ
    0.07
     "../../../../
    0.07
    èĶ·
    0.07
    teenth
    0.07
    Activations Density 0.389%

    No Known Activations