© 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. 41116
    Prev
    Next
    INDEX
    Explanations

    sources and information

    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
     kösz
    -0.08
    (es
    -0.08
    /null
    -0.08
    FileChooser
    -0.07
    çł´
    -0.07
    /she
    -0.07
    jenigen
    -0.07
    ecker
    -0.07
    ropri
    -0.07
    zonder
    -0.07
    POSITIVE LOGITS
     sources
    0.10
     information
    0.08
    forge
    0.08
     authoritative
    0.08
     authority
    0.08
     Ùħعت
    0.07
    olib
    0.07
    æ¸łéģĵ
    0.07
    人士
    0.07
    /source
    0.07
    Activations Density 0.025%

    No Known Activations