© 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. 58649
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences like $2n, 3n$

    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
    主ä¹īçļĦ
    -0.07
    ä½İçĤ¹
    -0.06
    ãĤŃãĥ£ãĥ³ãĥĹ
    -0.06
    çģ¯ç®±
    -0.06
    ؤ
    -0.06
    å½¼æѤçļĦ
    -0.06
    ä¹IJçļĦ
    -0.06
    ikit
    -0.06
    ere
    -0.06
    ÙĤÙħ
    -0.06
    POSITIVE LOGITS
    mente
    0.08
    almaz
    0.08
    ضة
    0.07
     -**
    0.07
    bservice
    0.07
    *_
    0.07
    **–
    0.07
     Naturalmente
    0.07
    æĬ¥äºĨ
    0.07
    warf
    0.07
    Activations Density 0.002%

    No Known Activations