© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings or identifiers

    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
    åŃĹæ¯į
    -0.08
    ellini
    -0.08
     opak
    -0.07
    çijĻ
    -0.07
    交æīĢ
    -0.07
    itamin
    -0.07
    太éĥİ
    -0.07
    ãĥĭãĥ³ãĤ°
    -0.07
    éĹ®é¢ĺæĿ¥äºĨ
    -0.07
    éij«
    -0.07
    POSITIVE LOGITS
     Beste
    0.06
    æľīçĹħ
    0.06
    æµ·å®ģ
    0.06
    帷å¹ķ
    0.06
    .git
    0.06
    idf
    0.06
    åĺ»
    0.06
    idge
    0.05
     ned
    0.05
     retro
    0.05
    Activations Density 0.077%

    No Known Activations