© 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. 60092
    Prev
    Next
    INDEX
    Explanations

    single, uniform, homogeneous

    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
    owie
    -0.09
    çŃĸ
    -0.08
    uzzi
    -0.08
    OwnProperty
    -0.07
    roscope
    -0.07
    паÑħ
    -0.07
    scopes
    -0.07
    skog
    -0.07
    -scal
    -0.07
    çĶµç½ij
    -0.07
    POSITIVE LOGITS
    åįķä¸Ģ
    0.20
    åįķä¸ĢçļĦ
    0.19
    åĸ®ä¸Ģ
    0.15
    /single
    0.15
     single
    0.14
     ëĭ¨ìĿ¼
    0.14
    (single
    0.14
     homogeneous
    0.13
     одноÑĢод
    0.13
    single
    0.12
    Activations Density 0.076%

    No Known Activations