© 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. 51042
    Prev
    Next
    INDEX
    Explanations

    physical sensations and feelings

    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
    å¿ĥçĹħ
    -0.08
    æĺĮ缼
    -0.08
    heu
    -0.08
    жи
    -0.08
    许æĦ¿
    -0.08
    emer
    -0.08
    eward
    -0.08
    igkeit
    -0.07
    burgh
    -0.07
    ely
    -0.07
    POSITIVE LOGITS
     sensations
    0.13
     sensation
    0.12
     feeling
    0.10
     оÑīÑĥÑīений
    0.10
    æĦŁåıĹ
    0.10
     Feel
    0.10
    触æĦŁ
    0.10
     feels
    0.09
     felt
    0.09
    æĦŁè§īåĪ°
    0.09
    Activations Density 0.051%

    No Known Activations