© 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. 23995
    Prev
    Next
    INDEX
    Explanations

    perception and sensation

    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
    ndata
    -0.08
    åİļåİļçļĦ
    -0.07
     banj
    -0.07
    enner
    -0.07
    éĹªçĿĢ
    -0.07
    éĵģè¡Ģ
    -0.07
    reven
    -0.07
    orr
    -0.07
     lucrative
    -0.07
    .house
    -0.07
    POSITIVE LOGITS
     perception
    0.12
     sensation
    0.11
    è§Ĩè§ī
    0.11
     subjective
    0.11
    主è§Ĥ
    0.11
     sensations
    0.11
    æĦŁçŁ¥
    0.10
     percept
    0.10
     Perception
    0.10
     perceived
    0.10
    Activations Density 0.090%

    No Known Activations