© 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. 45672
    Prev
    Next
    INDEX
    Explanations

    static

    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
    edException
    -0.11
    ings
    -0.10
    edList
    -0.09
    zelf
    -0.09
    intang
    -0.08
    jenigen
    -0.08
    çĨŁèĥ½
    -0.08
    ighed
    -0.08
    esh
    -0.08
    edImage
    -0.08
    POSITIVE LOGITS
    ally
    0.10
    ity
    0.09
    aily
    0.09
    amente
    0.09
    s
    0.09
     constexpr
    0.09
    د
    0.08
    ALLY
    0.08
    uously
    0.08
    ëĤĺë§Ī
    0.07
    Activations Density 0.027%

    No Known Activations