© 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. 29660
    Prev
    Next
    INDEX
    Explanations

    automatically generated content

    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
    est
    -0.07
    åŁºç¡ĢåĴĮ
    -0.06
     heavily
    -0.06
    infra
    -0.06
    åĢĴäºĨ
    -0.06
    æľĢåŁºæľ¬
    -0.06
    éĢģåĩº
    -0.06
    æĶ¾çĿĢ
    -0.06
    æĶ¾äºĨ
    -0.06
    èģĶæĴŃ
    -0.06
    POSITIVE LOGITS
    okok
    0.09
     hardcoded
    0.08
    olicited
    0.08
    ContentLoaded
    0.07
    iec
    0.07
    ä½ĵ
    0.07
    _CONSTANT
    0.07
    maa
    0.07
    oner
    0.07
    apper
    0.07
    Activations Density 0.002%

    No Known Activations