© 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. 645
    Prev
    Next
    INDEX
    Explanations

    charity, blocks, advertising, accommodation, risk

    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
    indsight
    -0.08
    envir
    -0.08
    ãĤ·ãĥ³ãĤ°
    -0.08
    ertools
    -0.08
     hels
    -0.08
    æĹłåıį
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    eyer
    -0.08
    æī«çłģåħ³æ³¨
    -0.08
    ombat
    -0.08
    POSITIVE LOGITS
    0.11
     [âĢ¦]
    0.10
     ...
    0.08
     [âĢ¦
    0.08
    \n
    0.08
     \"
    0.08
     (âĢ¦)
    0.08
     âĢİ
    0.07
     [...]
    0.07
    \"
    0.07
    Activations Density 0.114%

    No Known Activations