© 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. 60342
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
    cele
    -0.07
    kas
    -0.07
    ç²±
    -0.07
    ordin
    -0.06
    tim
    -0.06
     Plum
    -0.06
    m
    -0.06
    isValid
    -0.06
    Att
    -0.06
    ton
    -0.06
    POSITIVE LOGITS
    oja
    0.08
    éĻ¤äºĨåľ¨
    0.07
    ç¯Ħ
    0.07
    .decorate
    0.07
    rying
    0.07
    minated
    0.07
    çĶ¸
    0.07
    _mass
    0.07
    éħ¿
    0.07
     departed
    0.07
    Activations Density 0.005%

    No Known Activations