© 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. 22242
    Prev
    Next
    INDEX
    Explanations

    "ij", "sur", "wiÄħ", "ake"

    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
    ibat
    -0.08
    ipun
    -0.08
    ез
    -0.08
    áĥļáĥĶ
    -0.07
    MetaData
    -0.07
    xiety
    -0.07
     móc
    -0.07
    çİ°å®ŀ
    -0.07
    iena
    -0.07
    سÙĨ
    -0.07
    POSITIVE LOGITS
    uat
    0.07
     limit
    0.06
    /lic
    0.06
    ock
    0.06
    缴è¨Ģ
    0.06
    erken
    0.06
     roh
    0.06
    [:,:,
    0.06
    onet
    0.06
    icali
    0.06
    Activations Density 0.015%

    No Known Activations