© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    power converters and inverters

    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
    è¯ķ管
    -0.07
    観
    -0.06
     ident
    -0.06
    çIJĥèıĮ
    -0.06
     tal
    -0.06
     Carnegie
    -0.06
    å¤ļä¸Ģ份
    -0.06
    PTY
    -0.06
    çIJĥ
    -0.06
    çĻ
    -0.06
    POSITIVE LOGITS
    缴æµģ
    0.09
    æĸ©
    0.09
    æĸ¬
    0.09
    åıĺé¢ij
    0.08
    γο
    0.08
     PWM
    0.08
     Duty
    0.08
    freq
    0.08
    è°ĥéĢŁ
    0.08
    ä¸Ĭä¸Ģç«ł
    0.08
    Activations Density 0.069%

    No Known Activations