© 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. 4465
    Prev
    Next
    INDEX
    Explanations

    magnetic susceptibility measurements

    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
    Streams
    -0.09
    unga
    -0.08
    afx
    -0.08
    _cut
    -0.08
    伤
    -0.07
    åħĪè¿ĽçļĦæĬĢæľ¯
    -0.07
    çѱ
    -0.07
    幸åŃĺèĢħ
    -0.07
    ogl
    -0.06
    å¾Ħ
    -0.06
    POSITIVE LOGITS
     susceptibility
    0.08
     dope
    0.07
    æİ¥å¾ħ
    0.07
    agnet
    0.07
    ancel
    0.07
     coopér
    0.07
     lut
    0.07
    yat
    0.07
    ellis
    0.07
    Forms
    0.07
    Activations Density 0.004%

    No Known Activations