© 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. 22231
    Prev
    Next
    INDEX
    Explanations

    box dimensions

    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
    gnore
    -0.09
    zaak
    -0.08
    icke
    -0.08
    ìģ
    -0.07
    uzzi
    -0.07
    ossen
    -0.07
    ัà¸ģษ
    -0.07
     hoss
    -0.07
    ropolis
    -0.07
     volna
    -0.07
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.13
    avier
    0.10
    plorer
    0.10
    åĨħçļĦ
    0.10
     пеÑĢедаÑĩ
    0.10
    perience
    0.09
    plode
    0.09
    ercise
    0.09
    periments
    0.09
    perimental
    0.09
    Activations Density 0.049%

    No Known Activations