© 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. 49809
    Prev
    Next
    INDEX
    Explanations

    resonance, equilibrium, splicing

    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
    ĻĤ
    -0.08
    unya
    -0.08
    entifier
    -0.08
    rodu
    -0.07
    lay
    -0.07
    æģ¶æĢ§
    -0.07
    skon
    -0.07
    usif
    -0.07
    raga
    -0.07
    YGON
    -0.07
    POSITIVE LOGITS
     across
    0.07
    å¾ĢæĿ¥
    0.07
     distributes
    0.06
    peek
    0.06
     flap
    0.06
    æĬĬåŃ¦ä¹ł
    0.06
    æijĬ
    0.06
    altern
    0.06
    IID
    0.06
    ä¸Ńå°Ĩ
    0.06
    Activations Density 0.001%

    No Known Activations