© 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. 21424
    Prev
    Next
    INDEX
    Explanations

    balance between or among

    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
    aceous
    -0.08
    олÑĮ
    -0.08
    verläss
    -0.08
    ë¦Ħ
    -0.08
    รà¹īาย
    -0.07
    ลฯ
    -0.07
    -fashioned
    -0.07
    idel
    -0.07
    ually
    -0.07
    ether
    -0.07
    POSITIVE LOGITS
    loon
    0.09
    ยà¹Į
    0.09
    anced
    0.08
    -bal
    0.08
    encontre
    0.08
    zza
    0.08
    ÑĥÑİÑī
    0.08
    ford
    0.08
    ç§ĭæľĪ
    0.08
    -minded
    0.07
    Activations Density 0.021%

    No Known Activations