© 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. 28845
    Prev
    Next
    INDEX
    Explanations

    feel like / feel a / feel that

    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
    åĸľéĹ»
    -0.10
    auce
    -0.09
    evere
    -0.08
    emer
    -0.08
    ìĭľëĭ¤
    -0.08
    orris
    -0.08
    itory
    -0.08
    ÙĬÙĪÙĨ
    -0.08
    szak
    -0.08
    estos
    -0.08
    POSITIVE LOGITS
    uate
    0.10
    ings
    0.09
    uated
    0.08
    uating
    0.08
    ungsweise
    0.07
    ife
    0.07
    ä¸Ĭæĺ¯
    0.07
    ong
    0.06
    çĩ¥
    0.06
    åĴĮè¡Į为
    0.06
    Activations Density 0.051%

    No Known Activations