© 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. 31383
    Prev
    Next
    INDEX
    Explanations

    volume solvent volume volumes

    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
    yers
    -0.09
    æĪIJå¥Ĺ
    -0.08
    klus
    -0.08
    ainter
    -0.08
    æ¯ĶåĪ«äºº
    -0.08
    βε
    -0.08
    kaan
    -0.08
    zier
    -0.08
    arz
    -0.08
    ieto
    -0.08
    POSITIVE LOGITS
     volum
    0.07
     volume
    0.07
    volume
    0.07
    utsal
    0.07
     volumes
    0.07
    ä½ĵ积
    0.07
    æ°´çļĦ
    0.06
     volumen
    0.06
     solvent
    0.06
     slut
    0.06
    Activations Density 0.001%

    No Known Activations