© 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. 30904
    Prev
    Next
    INDEX
    Explanations

    Russian military involvement or condennation

    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
     dem
    -0.07
     synchronized
    -0.07
    åĻ
    -0.07
     deep
    -0.07
     synced
    -0.07
    .deep
    -0.06
    _coordinate
    -0.06
    éķ¿åº¦ä¸º
    -0.06
     restore
    -0.06
     restored
    -0.06
    POSITIVE LOGITS
    ówn
    0.08
     Dici
    0.07
     Terrace
    0.07
    rey
    0.07
    ±
    0.07
    olz
    0.07
    annis
    0.07
     Scaling
    0.07
    icky
    0.07
    æī¬éķ¿
    0.07
    Activations Density 0.007%

    No Known Activations