© 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. 21117
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols followed by equals or file extensions

    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
    лÑİ
    -0.07
    âĢ¦)
    -0.07
    atically
    -0.07
    reira
    -0.07
    ·
    -0.07
    èŃ°éķ·
    -0.06
    mgr
    -0.06
    åij½
    -0.06
    å°±
    -0.06
    âĢ¦âĢ¦
    -0.06
    POSITIVE LOGITS
    deaux
    0.08
    nof
    0.07
    ulli
    0.07
    æ¸Ī
    0.07
    éĵ¿
    0.07
    çıĬçıĬ
    0.07
    spo
    0.07
    çİ
    0.07
    çļĦä¸Ģ家
    0.06
    stantiate
    0.06
    Activations Density 0.006%

    No Known Activations