© 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. 50951
    Prev
    Next
    INDEX
    Explanations

    indirectly affected health conditions

    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
    edur
    -0.09
    gern
    -0.08
    .mid
    -0.08
     Kushner
    -0.08
    fach
    -0.07
    iliz
    -0.07
    stant
    -0.07
    ë¥
    -0.07
    mér
    -0.07
    assen
    -0.07
    POSITIVE LOGITS
     indirectly
    0.24
    éĹ´æİ¥
    0.23
     indirect
    0.21
     indire
    0.21
     INDIRECT
    0.15
    缴æİ¥æĪĸéĹ´æİ¥
    0.15
     gián
    0.14
    å½±åĵįåĪ°
    0.13
    ä¼ļå½±åĵįåĪ°
    0.12
    æ³¢åıĬ
    0.12
    Activations Density 0.261%

    No Known Activations