© 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. 19036
    Prev
    Next
    INDEX
    Explanations

    turbine and compressor

    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
    åİŁçĶŁ
    -0.06
    æ°¸ä¸į
    -0.06
    osl
    -0.06
    亲
    -0.06
    åħ¬å¾·
    -0.06
    æĢ»æķ°çļĦ
    -0.06
    ä¸ĢæŦåıijçİ°
    -0.06
    elop
    -0.06
    osc
    -0.06
    çĥ¤æ¼Ĩ
    -0.06
    POSITIVE LOGITS
     turbine
    0.09
    涡轮
    0.08
    ìĿµ
    0.08
    èĿ¶éĺĢ
    0.08
    女主è§Ĵ
    0.08
     inlet
    0.08
     izle
    0.08
     turbines
    0.07
     Apk
    0.07
    MinMax
    0.07
    Activations Density 0.019%

    No Known Activations