© 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. 18950
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    ibel
    -0.07
     beit
    -0.07
    rig
    -0.07
    çijŁ
    -0.07
    rame
    -0.07
    amis
    -0.07
    θεν
    -0.07
    åŃĺ
    -0.07
    utzen
    -0.07
    è·Ŀ
    -0.06
    POSITIVE LOGITS
    ãģ«ãģĭãģijãģ¦
    0.10
    åĨįåĪ°
    0.08
    abouts
    0.08
    inclusive
    0.08
    为æŃ¢
    0.07
    éĿŀåIJĮ
    0.07
     outright
    0.07
    bao
    0.07
    åŁł
    0.07
     inclusive
    0.07
    Activations Density 0.252%

    No Known Activations