© 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. 16252
    Prev
    Next
    INDEX
    Explanations

    start of sequences

    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
    å·¥ä½ľå²Ĺä½į
    -0.07
    ä¾Ŀæ³ķèĩªä¸»
    -0.07
    opus
    -0.07
    Hub
    -0.07
    obil
    -0.07
    åį¿
    -0.07
    XC
    -0.06
    ujet
    -0.06
    adge
    -0.06
    ombat
    -0.06
    POSITIVE LOGITS
    ReadStream
    0.08
    istri
    0.08
    èµ·å§ĭ
    0.07
    à¸ķรา
    0.07
    ä¸įåĢ¼
    0.07
    Initializing
    0.07
    ä¸ĩå²ģ
    0.07
    orton
    0.07
     starting
    0.07
    mula
    0.07
    Activations Density 0.014%

    No Known Activations