© 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. 26188
    Prev
    Next
    INDEX
    Explanations

    URL paths and code delimiters

    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
    âĢ¦**
    -0.08
    iec
    -0.08
    çĮĽè¿Ľ
    -0.08
    xfd
    -0.08
    ?):
    -0.08
    impa
    -0.08
    ebo
    -0.07
    zata
    -0.07
    initWith
    -0.07
     ('$
    -0.07
    POSITIVE LOGITS
     outright
    0.07
    ousse
    0.07
    دد
    0.06
     Demp
    0.06
    ÑĥмÑĭ
    0.06
    neb
    0.06
    éģ
    0.06
    alde
    0.06
    ardini
    0.06
    ologne
    0.05
    Activations Density 0.120%

    No Known Activations