© 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. 56402
    Prev
    Next
    INDEX
    Explanations

    i18n trans and LANG tokens

    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
    ä¸įèµ·çľ¼
    -0.07
    ÑģÑĤе
    -0.07
    rana
    -0.07
    alla
    -0.07
    lum
    -0.06
    rach
    -0.06
    /on
    -0.06
    éĵł
    -0.06
    rush
    -0.06
    Matchers
    -0.06
    POSITIVE LOGITS
    å¾
    0.07
    饶
    0.07
    iddle
    0.07
     домо
    0.07
    СÐŀ
    0.07
    ิยม
    0.06
    çļĩåŃIJ
    0.06
    aho
    0.06
     setempat
    0.06
    ifat
    0.06
    Activations Density 0.036%

    No Known Activations