© 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. 46203
    Prev
    Next
    INDEX
    Explanations

    code comments with javadoc style

    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
    -0.08
    ilog
    -0.07
    oun
    -0.07
    eners
    -0.06
    irk
    -0.06
    èī¯åĵģ
    -0.06
    åk
    -0.06
    auta
    -0.06
    ä»
    -0.06
    examen
    -0.06
    POSITIVE LOGITS
    ampe
    0.07
     Gres
    0.07
    éļ¾æ±Ĥ
    0.07
    afa
    0.07
    efs
    0.07
     erlä
    0.07
    AMP
    0.07
    ìķ½ìĿĦ
    0.07
    ONTAL
    0.07
    ä¹³
    0.07
    Activations Density 0.053%

    No Known Activations