© 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. 60767
    Prev
    Next
    INDEX
    Explanations

    other in

    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
    illet
    -0.08
    åijĬ
    -0.07
     Pantal
    -0.06
    arkin
    -0.06
     kompat
    -0.06
    DataStream
    -0.06
    æĸĻ
    -0.06
    天水
    -0.06
    icy
    -0.06
     heel
    -0.06
    POSITIVE LOGITS
     analogous
    0.12
     Analog
    0.10
     analogy
    0.10
     analogue
    0.10
     analog
    0.10
    ç±»æ¯Ķ
    0.09
     obdob
    0.08
    wers
    0.08
     ана
    0.08
    类似éĹ®é¢ĺ
    0.08
    Activations Density 0.597%

    No Known Activations