© 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. 50698
    Prev
    Next
    INDEX
    Explanations

    ions and chemical notations

    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
    uku
    -0.07
    itten
    -0.06
    ago
    -0.06
    çĨŁç»ĥæĵįä½ľ
    -0.06
    apor
    -0.06
    iato
    -0.06
    CKER
    -0.06
    éĩıçļĦ
    -0.06
    غة
    -0.06
    kede
    -0.06
    POSITIVE LOGITS
    letal
    0.08
    ÑģÑı
    0.08
     vare
    0.08
    vertime
    0.08
    ncy
    0.08
    Presenter
    0.08
    .sup
    0.07
    lare
    0.07
    ¿
    0.07
    ÙĦÙĩ
    0.07
    Activations Density 0.004%

    No Known Activations