© 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. 49279
    Prev
    Next
    INDEX
    Explanations

    numbers and code delimiters

    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
    æĤł
    -0.08
    livet
    -0.08
    ä¸ĥæľĪ
    -0.07
    eluk
    -0.07
    å¤§å®¶åľ¨
    -0.07
    ukkan
    -0.07
    ähr
    -0.07
    ehn
    -0.07
    enzio
    -0.07
    _gb
    -0.07
    POSITIVE LOGITS
    ONO
    0.07
    jax
    0.06
    antt
    0.06
    è¿IJåĬ¨
    0.06
    eis
    0.06
    ë§ĮìĹIJ
    0.06
     Ree
    0.06
     frequencies
    0.06
     numbers
    0.06
    anes
    0.06
    Activations Density 0.003%

    No Known Activations