© 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. 28671
    Prev
    Next
    INDEX
    Explanations

    HO, WAN, over, check, line, strategy, TIP, sclerosis, IC

    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
    "**
    -0.07
    âĢ¦**
    -0.07
    å¤Ħ
    -0.07
    ék
    -0.06
    èĬ±èIJ½
    -0.06
    &T
    -0.06
    ello
    -0.06
    çļĦéĩį
    -0.06
    ...**
    -0.06
    nu
    -0.06
    POSITIVE LOGITS
    ï¼ī
    0.12
    !),
    0.11
    âĪ·
    0.10
    ï¼īãĢį
    0.10
    !).
    0.09
    ï¼īãĥ»
    0.09
    ï¼īï¼Į
    0.09
    )
    0.09
    ï¼īãĢģ
    0.09
     ï¼ī
    0.09
    Activations Density 0.207%

    No Known Activations