© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44294
    Prev
    Next
    INDEX
    Explanations

    |e,n⟩ and |g,n-1⟩

    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
    Negative Logits
    -0.06
    âĤ¬,
    -0.06
     **
    -0.06
    éªij马
    -0.05
    )):
    -0.05
    '%(
    -0.05
    ))->
    -0.05
    殿
    -0.05
    âĢ¦,
    -0.05
    !!,
    -0.05
    POSITIVE LOGITS
    ⣩
    0.09
     vastaan
    0.09
    èĢĮçŁ¥
    0.08
    å¹½çģµ
    0.08
    agno
    0.08
    åħ®
    0.08
    rangle
    0.08
    WithError
    0.08
    ño
    0.08
    ourcing
    0.08
    Activations Density 0.001%

    No Known Activations