© 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. 4213
    Prev
    Next
    INDEX
    Explanations

    "literally" used as an intensifier

    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
    manship
    -0.12
    aan
    -0.09
    ered
    -0.08
    æĽ´åĪ«è¯´
    -0.08
    Ñģмо
    -0.07
    oule
    -0.07
    åĨķ
    -0.07
    ä¸įåīį
    -0.07
    abilidad
    -0.07
    erman
    -0.07
    POSITIVE LOGITS
    mente
    0.11
    amente
    0.10
    -minded
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    æĦıä¹īä¸Ĭ
    0.09
    ity
    0.08
    ly
    0.08
    enca
    0.08
    istically
    0.08
    keit
    0.08
    Activations Density 0.011%

    No Known Activations