© 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. 15411
    Prev
    Next
    INDEX
    Explanations

    Fibonacci sequence

    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
    æºĥ
    -0.08
    åħ´
    -0.08
    çĻ¾åĪĨä¹ĭçĻ¾
    -0.07
    大åIJī
    -0.07
    å®Įåħ¨çļĦ
    -0.07
    åĪĽåħĪäºīä¼ĺ
    -0.06
    å¼Ģæľį
    -0.06
    chung
    -0.06
    æīĵæĪIJ
    -0.06
    çĮ¿
    -0.06
    POSITIVE LOGITS
    onacci
    0.08
    bnb
    0.08
     Fibonacci
    0.07
     Growing
    0.07
    ãĥĬãĥ³
    0.07
    à¹ģà¸Ĺรà¸ģ
    0.07
    -cycle
    0.07
    èĬ½
    0.07
     recurrence
    0.07
    å¼łæµ·
    0.07
    Activations Density 0.004%

    No Known Activations