© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34724
    Prev
    Next
    INDEX
    Explanations

    NH compounds or abbreviations

    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
    nect
    -0.08
    aft
    -0.08
    anju
    -0.08
    nar
    -0.08
    lit
    -0.08
    ning
    -0.08
    Ø©
    -0.08
    als
    -0.08
    aal
    -0.08
    ryption
    -0.07
    POSITIVE LOGITS
    agas
    0.09
    ington
    0.07
    enticate
    0.07
    oad
    0.07
    olland
    0.07
    erring
    0.07
    ired
    0.07
    odge
    0.07
    à¸ģรัà¸IJมà¸Ļà¸ķรี
    0.07
    ciel
    0.07
    Activations Density 0.005%

    No Known Activations