© 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. 8071
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and sequences

    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
    äºĨæĮĩ
    -0.08
    erm
    -0.08
    afx
    -0.08
    缺ä¸Ģ
    -0.08
    ä¸ŃæĭĽ
    -0.07
     онкологи
    -0.07
    arah
    -0.07
    çĦ
    -0.07
    åħ¥åħļèªĵè¯į
    -0.07
    åĬŁäºİ
    -0.07
    POSITIVE LOGITS
    lessly
    0.06
     quotient
    0.06
    -stream
    0.06
    inous
    0.06
    澡
    0.06
    каÑĥ
    0.06
    <
    0.06
    oured
    0.06
    éĹĬ
    0.06
    odu
    0.06
    Activations Density 0.011%

    No Known Activations