© 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. 8091
    Prev
    Next
    INDEX
    Explanations

    referring to things

    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
    çļĦ
    -0.09
    âĢ¦âĢ¦ãĢĤ
    -0.07
    mente
    -0.07
    çļĦå°±
    -0.07
    onti
    -0.07
    Rnd
    -0.07
    @",
    -0.07
    VB
    -0.07
    å°±
    -0.06
    èį·
    -0.06
    POSITIVE LOGITS
    -même
    0.14
    /her
    0.13
    èĢģ人家
    0.12
    zelf
    0.12
    inerary
    0.10
    chy
    0.10
    SELF
    0.10
    self
    0.09
    unes
    0.09
    /us
    0.09
    Activations Density 0.259%

    No Known Activations