© 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. 12150
    Prev
    Next
    INDEX
    Explanations

    blueprint, segment, block, statement, chromosome

    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
    ика
    -0.08
    éĤ£äºĽäºº
    -0.07
     wund
    -0.07
    _IW
    -0.06
     circum
    -0.06
    à¸ŀ
    -0.06
    ows
    -0.06
    ä¸ĢåĪ»
    -0.06
    æĹłçĹĽäººæµģ
    -0.06
    ä¸Ģé»ŀ
    -0.06
    POSITIVE LOGITS
    blink
    0.08
    æłĸéľŀ
    0.08
    HU
    0.07
     biblio
    0.07
    RAR
    0.07
     bersangkutan
    0.07
    opil
    0.07
     isSelected
    0.07
     Jad
    0.07
    hek
    0.07
    Activations Density 0.621%

    No Known Activations