© 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. 38648
    Prev
    Next
    INDEX
    Explanations

    extremely followed by modifiers

    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
    edBy
    -0.09
    venes
    -0.09
    les
    -0.08
    less
    -0.08
    tera
    -0.08
    èĥľäºİ
    -0.08
    ceaux
    -0.08
    ÙĪØ·
    -0.08
    gable
    -0.08
    äºİä¸Ģ身
    -0.08
    POSITIVE LOGITS
    remely
    0.08
    ights
    0.08
    åħ¶ä¸Ń
    0.06
     nghiá»ĩm
    0.06
    ively
    0.06
    мож
    0.06
    å°ı
    0.06
    ãĤĤãģ®
    0.06
    oke
    0.06
    ernet
    0.06
    Activations Density 0.050%

    No Known Activations