© 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. 26099
    Prev
    Next
    INDEX
    Explanations

    boron compounds, borylation

    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
    ively
    -0.08
    ãģŁãĤĭ
    -0.07
    oris
    -0.07
    dam
    -0.06
    ivity
    -0.06
    çĬ¯äºĨ
    -0.06
     BÃŃ
    -0.06
     Black
    -0.06
    s
    -0.06
    saf
    -0.06
    POSITIVE LOGITS
    андÑĢ
    0.08
    apat
    0.08
     ÙħÙĨز
    0.08
    esium
    0.08
     männer
    0.08
     (;;
    0.08
    unate
    0.07
    ÙĬاس
    0.07
    иÑģÑĤ
    0.07
    ÑĢаÑħ
    0.07
    Activations Density 0.016%

    No Known Activations