© 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. 27100
    Prev
    Next
    INDEX
    Explanations

    elemental composition

    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
    siz
    -0.08
    imizer
    -0.08
    жан
    -0.08
    æºī
    -0.08
    otra
    -0.08
    illé
    -0.07
    æĨ§
    -0.07
    iors
    -0.07
    ynn
    -0.07
    sait
    -0.07
    POSITIVE LOGITS
    atomic
    0.07
    .Atomic
    0.07
     name
    0.07
    纪念å¸ģ
    0.07
    ially
    0.07
     whose
    0.07
    strup
    0.07
     atomic
    0.07
    Atomic
    0.07
    çŁ¿äº§
    0.07
    Activations Density 0.007%

    No Known Activations