© 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. 50106
    Prev
    Next
    INDEX
    Explanations

    state of new mexico

    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¤ľ
    -0.06
    ģ
    -0.06
    ı
    -0.06
    åijľ
    -0.06
    Å¡te
    -0.06
     fur
    -0.06
    ä¸įåĬł
    -0.06
    owell
    -0.06
    éģĹ
    -0.06
     whatever
    -0.06
    POSITIVE LOGITS
    -License
    0.08
    rapped
    0.08
    uhkan
    0.08
    (SIG
    0.08
     racked
    0.08
    머ëĭĪ
    0.07
    å°»
    0.07
    身ä¸Ĭä¸ĭ
    0.07
    -Length
    0.07
    å§Ķä»»
    0.07
    Activations Density 0.007%

    No Known Activations