© 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. 50300
    Prev
    Next
    INDEX
    Explanations

    English to German translations

    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
    èĥĥåı£
    -0.07
    fälle
    -0.07
    åı¯èĩªè¡Į
    -0.07
    otti
    -0.07
    为æŃ¢
    -0.06
    ysh
    -0.06
    fall
    -0.06
    ug
    -0.06
    æł¼æł¼
    -0.06
    mor
    -0.06
    POSITIVE LOGITS
    ael
    0.08
    bra
    0.07
    yss
    0.07
    转åĪ°
    0.07
    stag
    0.07
    ikon
    0.07
    uya
    0.07
    _outputs
    0.07
    ebel
    0.07
    anst
    0.07
    Activations Density 0.116%

    No Known Activations