© 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. 7049
    Prev
    Next
    INDEX
    Explanations

    as possible

    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
    Negative Logits
    oded
    -0.08
    è´µåľ¨
    -0.07
    aland
    -0.06
    apikey
    -0.06
     aga
    -0.06
     prim
    -0.06
    hares
    -0.06
    JAKARTA
    -0.06
    teles
    -0.06
    ç§įåħ»
    -0.06
    POSITIVE LOGITS
     imaginable
    0.14
    å°½åı¯èĥ½
    0.13
    å°½åı¯èĥ½çļĦ
    0.13
     possible
    0.12
     available
    0.12
     necessary
    0.12
    possible
    0.12
    å°½åı¯èĥ½åľ°
    0.11
     posible
    0.11
    _available
    0.11
    Activations Density 0.277%

    No Known Activations