© 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. 8613
    Prev
    Next
    INDEX
    Explanations

    volume units

    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
    μαν
    -0.07
    ä¸ĢæľĿ
    -0.07
    alist
    -0.07
     autogenerated
    -0.06
    èĩ»
    -0.06
    inken
    -0.06
    öne
    -0.06
     ведом
    -0.06
    åĶ¯æľī
    -0.06
    ÙĨدÛĮ
    -0.06
    POSITIVE LOGITS
     aliqu
    0.12
    æł·åĵģ
    0.11
    æłĩæľ¬
    0.10
    /sample
    0.10
     samples
    0.09
     Samples
    0.09
     specimens
    0.09
    åıĸæł·
    0.09
    æł·æľ¬
    0.09
    sample
    0.09
    Activations Density 0.019%

    No Known Activations