© 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. 44901
    Prev
    Next
    INDEX
    Explanations

    rare earth elements

    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
    éĩı身å®ļåĪ¶
    -0.09
    øy
    -0.08
    –and
    -0.07
     компÑĮÑİÑĤеÑĢ
    -0.07
     intimid
    -0.07
    -0.07
     COMPUTER
    -0.07
    _plus
    -0.07
    è¾¾æĪIJåħ±è¯Ĩ
    -0.07
     lass
    -0.07
    POSITIVE LOGITS
    RIA
    0.07
    åıĺæĢģ
    0.07
     Hermann
    0.07
     Äįás
    0.06
    Uber
    0.06
     лега
    0.06
     Ia
    0.06
    éĿŀ常丰å¯Į
    0.06
     вÑĤоÑĢÑĭ
    0.06
     Sachs
    0.06
    Activations Density 0.036%

    No Known Activations