© 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. 60541
    Prev
    Next
    INDEX
    Explanations

    reference endings

    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
    示
    -0.06
    zny
    -0.06
    èĩ´
    -0.06
    éĢĹ
    -0.06
    离
    -0.06
    raph
    -0.06
    IZES
    -0.06
    座
    -0.06
    åĨ·åĵ¼
    -0.06
     seder
    -0.05
    POSITIVE LOGITS
    .super
    0.08
    utely
    0.08
    å¦Ĥèį¼
    0.08
    baugh
    0.08
    atil
    0.08
    åĭģ
    0.08
    alley
    0.08
    kert
    0.07
    ä¸Ĭåįĥ
    0.07
    ited
    0.07
    Activations Density 0.071%

    No Known Activations