© 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. 47411
    Prev
    Next
    INDEX
    Explanations

    95% confidence intervals

    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
    она
    -0.08
    inov
    -0.08
    èIJ¥åķĨ
    -0.08
    IPHER
    -0.08
    iná
    -0.07
    .descriptor
    -0.07
     Vinci
    -0.07
    еÑĩа
    -0.07
    缸æĢĿ
    -0.07
    dÃŃ
    -0.07
    POSITIVE LOGITS
    oral
    0.06
     Pilar
    0.06
     Atlan
    0.06
     nowrap
    0.06
    éģĵå¾·
    0.06
     Globe
    0.06
    robe
    0.06
    reation
    0.06
     Republik
    0.06
    åħ¶çĥ¦
    0.05
    Activations Density 0.002%

    No Known Activations