© 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. 62294
    Prev
    Next
    INDEX
    Explanations

    documentation arguments

    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
     Sos
    -0.07
     Destin
    -0.07
    æĺ¥èī²
    -0.07
    owitz
    -0.06
    able
    -0.06
    å±ħçĦ¶
    -0.06
    ç§ĭèī²
    -0.06
    दान
    -0.06
    ç«Ł
    -0.06
    æĺ¥åįİ
    -0.06
    POSITIVE LOGITS
    åıĬè¦ģæ±Ĥ
    0.08
    ož
    0.08
    .every
    0.07
    üst
    0.07
    blr
    0.07
    žd
    0.07
    antal
    0.07
    .std
    0.07
    ÙħÙĨت
    0.07
    .progress
    0.07
    Activations Density 0.001%

    No Known Activations