© 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. 23850
    Prev
    Next
    INDEX
    Explanations

    elaboration, context, or correction

    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
    ajer
    -0.08
    ján
    -0.08
    epen
    -0.07
    isiv
    -0.07
    模
    -0.07
    argas
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    uten
    -0.07
    arder
    -0.07
    jeÄį
    -0.07
    POSITIVE LOGITS
    roc
    0.08
    APPER
    0.08
     -:
    0.07
    ëĬ
    0.07
    以西
    0.07
    à¹įา
    0.06
    iera
    0.06
    icker
    0.06
    *:
    0.06
    åıĤåĬłéĿ¢è¯ķ
    0.06
    Activations Density 0.014%

    No Known Activations