© 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. 24559
    Prev
    Next
    INDEX
    Explanations

    numbers, special characters, and code snippets

    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
    ç¼
    -0.07
    вал
    -0.06
    à°Ĺ
    -0.06
     Cor
    -0.06
    èİ·å¾Ĺ
    -0.06
     overl
    -0.06
    è¾ħåĬ©
    -0.06
     Buzz
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
    é
    -0.06
    POSITIVE LOGITS
    ascript
    0.10
    lobber
    0.09
     podsta
    0.08
     recru
    0.08
    Compiled
    0.08
    menta
    0.08
    hores
    0.08
    ergie
    0.08
    Namespace
    0.08
    FRING
    0.08
    Activations Density 0.003%

    No Known Activations