© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17867
    Prev
    Next
    INDEX
    Explanations

    redundant, already, twice, compressed, well

    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
    że
    -0.08
    гое
    -0.07
    itzer
    -0.07
    attes
    -0.07
    åħ³ç³»åĪ°
    -0.07
    igs
    -0.06
     Distrib
    -0.06
    èIJ©
    -0.06
    à¯ģà®ķ
    -0.06
    ä¸ĵæ¡Ī
    -0.06
    POSITIVE LOGITS
    åıĮéĩį
    0.15
     redund
    0.15
     redundant
    0.13
    çļĦåıĮéĩį
    0.13
    åıłåĬł
    0.13
    éĩįå¤į
    0.13
    éĩįè¤ĩ
    0.13
    à¸ĭà¹īำ
    0.13
     dopp
    0.12
     already
    0.12
    Activations Density 0.193%

    No Known Activations