© 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. 16994
    Prev
    Next
    INDEX
    Explanations

    extrapolation

    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
     ".",
    -0.07
    ÄŁÃ¼
    -0.07
    Ñįй
    -0.07
    æľĢ大ç¨ĭ度
    -0.07
     Ria
    -0.07
     Noël
    -0.07
    adia
    -0.07
    abra
    -0.07
    ogy
    -0.07
    bie
    -0.07
    POSITIVE LOGITS
    OrCreate
    0.08
     thereof
    0.08
    åIJİåı¯
    0.07
    poses
    0.07
    ablish
    0.07
    çħ§
    0.07
    _embeddings
    0.07
    åIJİæľī
    0.07
    irl
    0.07
    ÙĤاد
    0.07
    Activations Density 0.010%

    No Known Activations