© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17277
    Prev
    Next
    INDEX
    Explanations

    formal, formally

    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
    -0.09
    stral
    -0.09
    aspers
    -0.08
    eens
    -0.08
    åĴĮå¤ĦçIJĨ
    -0.08
    aista
    -0.08
    ÏĨÏĮ
    -0.08
    аем
    -0.08
    annis
    -0.07
    Ĺ
    -0.07
    POSITIVE LOGITS
    dehyde
    0.15
    ities
    0.13
    mente
    0.12
    ized
    0.11
    ity
    0.09
    idades
    0.09
    åħ¶äºĭ
    0.09
    åĮĸçļĦ
    0.09
    ization
    0.09
    ize
    0.09
    Activations Density 0.025%

    No Known Activations