© 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. 63605
    Prev
    Next
    INDEX
    Explanations

    "Not" followed by uncertainty or limits

    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
    elves
    -0.08
    erness
    -0.08
    à¸Ľà¸£
    -0.07
    Ñĸз
    -0.07
    cito
    -0.07
    ersist
    -0.07
    èĥ§
    -0.07
    CREEN
    -0.07
    ontre
    -0.07
    upon
    -0.07
    POSITIVE LOGITS
    íĭĢ
    0.09
    ä½łæĪij
    0.08
    Ø©
    0.08
    iems
    0.08
     vorba
    0.07
    ewise
    0.07
    zet
    0.07
    åĬłæĭ¿å¤§
    0.07
     necessarily
    0.07
    etheless
    0.07
    Activations Density 0.033%

    No Known Activations