© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23105
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    dei
    -0.09
    enas
    -0.08
    大åįĥ
    -0.07
    lyn
    -0.07
    à¹Ģà¸ģลà¹īา
    -0.07
    uo
    -0.07
    ÑħÑĢо
    -0.06
    彬
    -0.06
    群ä¼ĹåĬŀå®ŀäºĭ
    -0.06
    /cs
    -0.06
    POSITIVE LOGITS
    opcion
    0.07
    款
    0.07
    æīģ
    0.06
     fo
    0.06
    stood
    0.06
    gnore
    0.06
     gama
    0.06
    weiler
    0.06
    oleon
    0.06
    elic
    0.06
    Activations Density 0.001%

    No Known Activations