© 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. 4455
    Prev
    Next
    INDEX
    Explanations

    possessions, personal items

    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
    erii
    -0.10
    eria
    -0.09
    eri
    -0.09
    à¹Ģà¸Ķียว
    -0.09
    glieder
    -0.09
    asiun
    -0.09
    amá
    -0.08
    erio
    -0.08
    erÃŃa
    -0.08
    erias
    -0.08
    POSITIVE LOGITS
    ändig
    0.11
    elves
    0.10
    verständlich
    0.10
    ständig
    0.10
    thing
    0.08
     behalf
    0.08
    ändige
    0.07
    ä½ľåĪĻ
    0.07
    ê²ĥ
    0.07
     vol
    0.06
    Activations Density 0.028%

    No Known Activations