© 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. 9471
    Prev
    Next
    INDEX
    Explanations

    work cost

    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
    æľĿ天
    -0.09
    uve
    -0.08
    夫æĸ¯åŁº
    -0.08
     пÑĢоÑģÑĤÑĥ
    -0.08
    rips
    -0.07
    coverage
    -0.07
    è¦Ĩ
    -0.07
    天çĽĸ
    -0.07
    ÐĵС
    -0.07
    åħ¨è¦ĨçĽĸ
    -0.07
    POSITIVE LOGITS
     theoretically
    0.08
    æľĢå¤ļ
    0.08
     Carn
    0.07
     motive
    0.07
    榨
    0.07
     harness
    0.07
     reversible
    0.07
    nable
    0.07
    ã
    0.07
     efficiency
    0.07
    Activations Density 0.005%

    No Known Activations