© 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. 14984
    Prev
    Next
    INDEX
    Explanations

    names ending with specific suffixes

    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
     "{"
    -0.07
    Ñįй
    -0.07
    书记
    -0.07
    ãģĽ
    -0.07
    ific
    -0.07
    inq
    -0.06
    elic
    -0.06
    olog
    -0.06
    rame
    -0.06
    ivet
    -0.06
    POSITIVE LOGITS
    -&
    0.07
    ersten
    0.07
    娥
    0.07
    ampf
    0.07
    icke
    0.07
    weiler
    0.07
     koÄįi
    0.07
    RelativeTo
    0.07
    ï½¥
    0.07
    ä¸įä¼ļæľī
    0.06
    Activations Density 0.020%

    No Known Activations