© 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. 31028
    Prev
    Next
    INDEX
    Explanations

    phthalate/phthalocyanine precursors

    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
    essel
    -0.07
    egos
    -0.07
    xes
    -0.07
    ibble
    -0.07
    åħĭçļĦ
    -0.07
    زÙĨØ©
    -0.07
    ern
    -0.07
    -0.06
    hest
    -0.06
    太è¡Į
    -0.06
    POSITIVE LOGITS
    åħ¥ãĤĬ
    0.08
    mil
    0.07
    é¢łåĢĴ
    0.07
    èľĢ
    0.07
    ãĥŃãĥ¼ãĤº
    0.07
    activ
    0.07
    åĪĺ强
    0.07
     activ
    0.07
    à¸Ľà¸´
    0.07
    ia
    0.06
    Activations Density 0.001%

    No Known Activations