© 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. 25854
    Prev
    Next
    INDEX
    Explanations

    repel, repulsion, repugnant, repudiate

    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
    urer
    -0.09
    erman
    -0.09
    cules
    -0.08
    uments
    -0.08
    eca
    -0.08
    dle
    -0.08
    vette
    -0.08
    evers
    -0.08
    .DataTable
    -0.08
    ç¹ģèĬ±
    -0.08
    POSITIVE LOGITS
    ive
    0.10
     nhau
    0.10
    ively
    0.08
    isson
    0.08
    ington
    0.08
    unic
    0.07
    ulsive
    0.07
    avig
    0.07
    ulent
    0.07
    /ref
    0.07
    Activations Density 0.003%

    No Known Activations