© 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. 22382
    Prev
    Next
    INDEX
    Explanations

    special characters or emojis

    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
    沿è¡Ĺ
    -0.07
    ÑĨÑĮ
    -0.07
    çķ¦
    -0.07
    aur
    -0.07
    ighted
    -0.07
    furt
    -0.07
    shire
    -0.07
    itol
    -0.07
    ÙĪØ©
    -0.07
    rible
    -0.07
    POSITIVE LOGITS
    ðŁ
    0.08
    æľŃ
    0.07
    ħ
    0.07
    clist
    0.07
    quete
    0.07
    ASI
    0.07
    æĶ¯æĮģä¸İ
    0.06
    zne
    0.06
    åĺ¿
    0.06
    isl
    0.06
    Activations Density 0.003%

    No Known Activations