© 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. 55930
    Prev
    Next
    INDEX
    Explanations

    taste, flavor, sensation, feeling

    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
     unlucky
    -0.07
    æĤ²æĥ¨
    -0.07
    å¯ħ
    -0.07
    羨
    -0.07
     inefficient
    -0.07
     desperate
    -0.07
    éĢł
    -0.07
    çģ°å¿ĥ
    -0.07
     disgrace
    -0.07
     damning
    -0.07
    POSITIVE LOGITS
     ëĬIJê»´
    0.11
     оÑīÑĥÑīениÑı
    0.11
     оÑīÑĥÑīение
    0.11
     sensation
    0.10
     feel
    0.10
     sensations
    0.10
    æĦŁè§ī
    0.10
    çļĦæĦŁè§ī
    0.10
    涩
    0.10
     feeling
    0.10
    Activations Density 0.106%

    No Known Activations