© 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. 28426
    Prev
    Next
    INDEX
    Explanations

    ejection fraction

    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
    å¾Ĵ
    -0.08
     cheats
    -0.07
    elier
    -0.07
    æºħ
    -0.07
    -news
    -0.07
    ILES
    -0.07
    à¸¸à¸Ľ
    -0.07
    kons
    -0.07
    agal
    -0.07
    ILLE
    -0.07
    POSITIVE LOGITS
    åĪļ
    0.08
    Õµ
    0.08
    à¸Ħ
    0.07
    å¿ĥçĶĺæĥħæĦ¿
    0.07
    åĪļä¸Ģ
    0.07
    åīĽ
    0.07
    士
    0.07
    ECTR
    0.06
    ç°§
    0.06
     Ali
    0.06
    Activations Density 0.212%

    No Known Activations