© 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. 46204
    Prev
    Next
    INDEX
    Explanations

    `redirect` to, `mov` q, `/path` to, `name` | index

    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
    à¦ŀ
    -0.06
    ukul
    -0.06
    ¯
    -0.06
    archy
    -0.06
    agan
    -0.06
    /navbar
    -0.06
    uerta
    -0.06
     {}",
    -0.06
    ARGV
    -0.05
    æį®æѤ
    -0.05
    POSITIVE LOGITS
    etheless
    0.10
    adays
    0.10
    bsites
    0.09
    odore
    0.09
    ÙĢÙĢÙĢÙĢÙĢ
    0.09
    ÙĢÙĢÙĢÙĢÙĢÙĢÙĢÙĢ
    0.09
    åŃIJæĽ°
    0.09
    ³³³
    0.08
     infatti
    0.08
     nemlig
    0.08
    Activations Density 0.356%

    No Known Activations