© 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. 11394
    Prev
    Next
    INDEX
    Explanations

    the `the` and `it`

    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
    iment
    -0.06
    rus
    -0.06
    ÂŃs
    -0.06
    iform
    -0.06
    è¢ħ
    -0.06
    atab
    -0.06
    rador
    -0.06
    Deque
    -0.06
    äºķ
    -0.06
    caled
    -0.06
    POSITIVE LOGITS
    zni
    0.10
    _codegen
    0.08
    _lite
    0.07
    åħ¨ä¼ļ
    0.07
    akens
    0.07
    anju
    0.07
    ÐŃС
    0.07
    ICIO
    0.07
    èĩ³ä»Ĭå·²æľī
    0.07
    UGHT
    0.07
    Activations Density 0.057%

    No Known Activations