© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    samples and specimens

    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
    使å®ĥ
    -0.07
    秫
    -0.07
    æss
    -0.07
    çı
    -0.06
    attering
    -0.06
    åĪĨç«ĭ
    -0.06
    æºī
    -0.06
    综
    -0.06
     flick
    -0.06
     ì¡°ìłķ
    -0.06
    POSITIVE LOGITS
     samples
    0.17
    æł·æľ¬
    0.15
     Samples
    0.14
    éĩĩæł·
    0.14
    æł·åĵģ
    0.14
    samples
    0.14
    Samples
    0.14
    éĩĩéĽĨ
    0.14
     sampel
    0.13
    _samples
    0.13
    Activations Density 0.468%

    No Known Activations