© 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. 56651
    Prev
    Next
    INDEX
    Explanations

    bonds, pumping, molecules, stoichiometry

    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
    راد
    -0.08
    ุà¸ģ
    -0.08
    -IS
    -0.08
    acor
    -0.08
    çĿ¦
    -0.08
    hurst
    -0.08
    Ỽt
    -0.08
    ulli
    -0.08
    EIC
    -0.08
     verkl
    -0.07
    POSITIVE LOGITS
     net
    0.09
    net
    0.09
    åĩĢ
    0.08
     Net
    0.08
     per
    0.07
    oret
    0.07
     nett
    0.07
     theoretically
    0.07
    Net
    0.07
    /net
    0.07
    Activations Density 0.005%

    No Known Activations