© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    庶
    -0.06
    _DU
    -0.06
    .none
    -0.06
    åİ®
    -0.06
     Geg
    -0.06
    第äºĮæĿ¡
    -0.06
    äºĶæľĪ
    -0.06
     thing
    -0.06
    æī«åľ°
    -0.06
    nia
    -0.06
    POSITIVE LOGITS
    å°ıæľī
    0.09
    è¿Ħä»Ĭ
    0.08
    holm
    0.08
    ÑĢаÑĤно
    0.07
     Karr
    0.07
    ebles
    0.07
     pikk
    0.07
    æĸ°å®¢æĪ·
    0.07
    ottes
    0.07
    試çĶ¨
    0.07
    Activations Density 0.010%

    No Known Activations