© 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. 2395
    Prev
    Next
    INDEX
    Explanations

    owns, generate, Save, output, were, spend

    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
    çĶļèĩ³æĺ¯
    -0.07
    è±ģ
    -0.07
    että
    -0.07
    aman
    -0.07
    æĺ¯ä¸ĢäºĽ
    -0.06
    jent
    -0.06
    ä¸Ģç§Ĵ
    -0.06
    utor
    -0.06
    appar
    -0.06
    berto
    -0.06
    POSITIVE LOGITS
    omme
    0.08
    æłĩåĩĨ为
    0.08
    hsi
    0.07
    èĭ¥å¹²
    0.07
    inh
    0.07
    OMPI
    0.07
     Scalars
    0.07
    /render
    0.06
    å¤ļå°ij
    0.06
    omé
    0.06
    Activations Density 0.006%

    No Known Activations