© 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. 44408
    Prev
    Next
    INDEX
    Explanations

    magnetic field, cam, fire, laser, optical, eccentric

    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
     participant
    -0.07
     intertwined
    -0.06
    åĢĴ
    -0.06
     partecipanti
    -0.06
    variant
    -0.06
     particular
    -0.06
    ios
    -0.06
    -slot
    -0.06
    track
    -0.06
    INLINE
    -0.06
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.09
    对å®ĥ
    0.08
    uhan
    0.08
    åİĭä¸ĭ
    0.08
    åĪ°æĿ¥
    0.08
     trigger
    0.08
    æĭīå¾·
    0.08
    踵
    0.08
    对åħ¶
    0.08
    edal
    0.08
    Activations Density 0.138%

    No Known Activations