© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    LTR, AT, furnace, stamps

    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
    .constructor
    -0.08
    uale
    -0.08
    å®Ŀå¡Ķ
    -0.07
    충
    -0.07
    å®Ĺ
    -0.07
    æľªæĪIJå¹´
    -0.07
    éħ±
    -0.07
    èݹ
    -0.07
    åIJĪä½ĵ
    -0.07
    chin
    -0.07
    POSITIVE LOGITS
    æĮĩ
    0.07
    åIJİåį³
    0.07
    åį³åĪ°
    0.07
    å°±æĺ¯æĮĩ
    0.07
    å°±æĺ¯è¿Ļ个
    0.06
    angk
    0.06
    æĮĩçļĦæĺ¯
    0.06
    éĩį
    0.06
     referring
    0.06
    ä¹Łå°±æĺ¯
    0.06
    Activations Density 0.015%

    No Known Activations