© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11134
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions or symbols

    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
     dim
    -0.06
    è¶Ĭèµ°
    -0.06
     Holmes
    -0.06
    èĥ½å¤Łå°Ĩ
    -0.06
    ully
    -0.06
    otec
    -0.06
    .template
    -0.06
    éķ¿è¾¾
    -0.06
    cate
    -0.05
    athed
    -0.05
    POSITIVE LOGITS
    Markup
    0.08
    :_
    0.08
    erer
    0.08
    éĤ£ä¸ªæŶåĢĻ
    0.08
    umbs
    0.07
    éħİ
    0.07
    **–
    0.07
    èĩ
    0.07
    COLUMN
    0.07
    PropertyValue
    0.07
    Activations Density 0.002%

    No Known Activations