© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30000
    Prev
    Next
    INDEX
    Explanations

    foreign language translation questions

    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
    å¦Ĥ对
    -0.07
    pflicht
    -0.07
    级以ä¸Ĭ
    -0.07
    aven
    -0.07
    åĪĨåĪĨéĴŁ
    -0.07
    åIJįåĪĹ
    -0.07
    å¦ĤæĹł
    -0.07
     Mayer
    -0.06
    Ĵáŀ
    -0.06
    —and
    -0.06
    POSITIVE LOGITS
    translator
    0.08
    |array
    0.07
    è¯ij为
    0.07
    ç¿»è¯ij
    0.07
    Textarea
    0.07
    (Arg
    0.07
    azen
    0.07
    ÙĨدÙĩ
    0.07
    enie
    0.06
    steen
    0.06
    Activations Density 0.055%

    No Known Activations