© 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. 32362
    Prev
    Next
    INDEX
    Explanations

    olfactory and gustatory systems

    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¥Ĺ
    -0.07
     accumulated
    -0.07
    ragment
    -0.07
     turnaround
    -0.07
    æĮī计åĪĴ
    -0.07
     Ale
    -0.06
    åįĹæµ·
    -0.06
    Readable
    -0.06
     Silva
    -0.06
    身å¿ĥ
    -0.06
    POSITIVE LOGITS
    åij³è§ī
    0.11
    触è§ī
    0.10
     receptors
    0.09
     sensory
    0.08
    /color
    0.08
     ÑģенÑģоÑĢ
    0.08
    åij³èķ¾
    0.08
     sensations
    0.08
     trist
    0.08
     disgust
    0.08
    Activations Density 0.020%

    No Known Activations