© 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. 32293
    Prev
    Next
    INDEX
    Explanations

    comma separated values

    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
    nee
    -0.08
    _stuff
    -0.07
    jne
    -0.07
    Ãłi
    -0.07
    mal
    -0.07
    èĥĥçĹħ
    -0.07
    edig
    -0.07
    éģ¥è¿ľçļĦ
    -0.07
    ingk
    -0.07
    æľ¬çıŃ
    -0.07
    POSITIVE LOGITS
    ÙĪÛĮÙĩ
    0.08
    ¦
    0.08
    ikum
    0.08
     olup
    0.07
    åħ¬æīĢ
    0.07
    ²
    0.07
     prak
    0.07
    å¾·éŁ³
    0.07
    æĿī
    0.06
    amol
    0.06
    Activations Density 0.018%

    No Known Activations