© 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. 23666
    Prev
    Next
    INDEX
    Explanations

    objective c or objectives

    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
    ers
    -0.10
    ackle
    -0.08
    acks
    -0.08
    thest
    -0.07
    à¹Ĩ
    -0.07
    atab
    -0.07
    oting
    -0.07
    жом
    -0.07
    lacement
    -0.07
    ibilidade
    -0.07
    POSITIVE LOGITS
    ãĤĤãģĹãĤį
    0.09
    ehme
    0.09
    Crud
    0.09
    uary
    0.08
    ech
    0.08
    Reached
    0.08
    RAIN
    0.08
    uvre
    0.08
    TypeDef
    0.08
    -driven
    0.08
    Activations Density 0.025%

    No Known Activations