© 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. 38464
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    ä¾Ľ
    -0.07
    enheim
    -0.07
    ango
    -0.07
    èĦ±ç¦»äºĨ
    -0.06
    oso
    -0.06
    人æĹł
    -0.06
    ENTRY
    -0.06
    ä¼ĺåĬ£
    -0.06
    ient
    -0.06
    esh
    -0.06
    POSITIVE LOGITS
    counts
    0.09
    计æķ°
    0.08
     count
    0.08
    å¹³åĿĩæ¯ı
    0.08
     expectancy
    0.08
    æľŁæľĽ
    0.08
    ITOS
    0.08
    ãĤ«ãĤ¦ãĥ³ãĥĪ
    0.08
     counting
    0.08
     counts
    0.08
    Activations Density 0.005%

    No Known Activations