© 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. 57465
    Prev
    Next
    INDEX
    Explanations

    percentages and concentrations

    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
    ׳×Ļ×Ķ
    -0.08
    é¦
    -0.07
    饥
    -0.07
    西éĽħ
    -0.07
    iman
    -0.06
    京åħ¬ç½ijå®īå¤ĩ
    -0.06
    èģĺ
    -0.06
    iska
    -0.06
    çĽĺæ´»
    -0.06
    è³
    -0.06
    POSITIVE LOGITS
     (%)
    0.08
    _percent
    0.08
     concentración
    0.08
     concentrate
    0.08
    igm
    0.08
     concentration
    0.07
    æ¯ħ
    0.07
    percentage
    0.07
    hibited
    0.07
    æµĵ度
    0.07
    Activations Density 0.038%

    No Known Activations