© 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. 31139
    Prev
    Next
    INDEX
    Explanations

    umlauts and accented characters

    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
    rieb
    -0.08
    osso
    -0.08
    chow
    -0.08
    ingham
    -0.08
    ossos
    -0.07
    úi
    -0.07
    ulich
    -0.07
    绿洲
    -0.07
    ajer
    -0.07
    oyer
    -0.07
    POSITIVE LOGITS
     Unicode
    0.08
     lingu
    0.08
     phon
    0.07
     unicode
    0.07
     pronunciation
    0.07
    Unicode
    0.07
    è·¯éĢı
    0.07
    åıijéŁ³
    0.07
     Romance
    0.07
     dialect
    0.07
    Activations Density 0.029%

    No Known Activations