© 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. 43423
    Prev
    Next
    INDEX
    Explanations

    accompanying or alongside

    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
    omio
    -0.09
    ebol
    -0.08
    ãĥĤ
    -0.08
    menti
    -0.08
    лии
    -0.08
    alni
    -0.08
    åħ«ä»Ļ
    -0.08
    chestra
    -0.07
    mitglied
    -0.07
    PyObject
    -0.07
    POSITIVE LOGITS
     accompanies
    0.08
     accompany
    0.08
    èĢĮéĿŀ
    0.07
     accompanying
    0.07
    ä¸įçľĭ
    0.07
    éħįåIJĪ
    0.06
     aspect
    0.06
    adam
    0.06
     Aspect
    0.06
     alongside
    0.06
    Activations Density 0.463%

    No Known Activations