© 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. 18587
    Prev
    Next
    INDEX
    Explanations

    Haskell programming language constructs

    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
    æĬ¬å¤´
    -0.08
    (android
    -0.07
    çijľ
    -0.07
    ç»Ŀåľ°
    -0.07
    roi
    -0.07
    .Toolkit
    -0.07
    çºł
    -0.07
    èĥģè¿«
    -0.07
    ogg
    -0.07
    arris
    -0.07
    POSITIVE LOGITS
     Turing
    0.08
     bytecode
    0.08
    _recursive
    0.08
     Recursive
    0.08
     recursive
    0.08
    ützen
    0.08
     synt
    0.08
    ãĤ¹ãĥĪãĥ¼ãĥ«
    0.08
    ibil
    0.08
     Lisp
    0.08
    Activations Density 0.016%

    No Known Activations