© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55072
    Prev
    Next
    INDEX
    Explanations

    behind, to the side, across

    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
    Negative Logits
    足
    -0.07
     rát
    -0.07
     ode
    -0.07
    ots
    -0.07
    åķĨ
    -0.07
    _CHILD
    -0.07
    intis
    -0.07
     mus
    -0.07
    åĹĵ
    -0.07
     measure
    -0.06
    POSITIVE LOGITS
     opposite
    0.10
    ivu
    0.08
     пÑĢоÑĤивополо
    0.07
    Opp
    0.07
     opposing
    0.07
     opponent
    0.07
    VAN
    0.07
    ijIJ
    0.07
     Prosp
    0.07
     direction
    0.07
    Activations Density 0.001%

    No Known Activations