© 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. 26303
    Prev
    Next
    INDEX
    Explanations

    note followed by colon

    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
    以å¾ħ
    -0.08
    anos
    -0.08
    ÛĮشاÙĨ
    -0.08
    sel
    -0.08
    eli
    -0.07
    çIJĨ论水平
    -0.07
    åģıåģı
    -0.07
    ানà§ĩ
    -0.07
    ä»ĸçªģçĦ¶
    -0.07
    evi
    -0.07
    POSITIVE LOGITS
    ï¼ļ
    0.10
    .:
    0.08
    !!:
    0.08
    åıĬè¦ģæ±Ĥ
    0.08
    :
    0.08
    åĶı
    0.07
    ï¼ļ“
    0.07
    ĩ
    0.07
    ï¼ļ"
    0.07
    geber
    0.07
    Activations Density 0.055%

    No Known Activations