© 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. 2504
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĤ
    -0.07
    ai
    -0.07
     mon
    -0.06
    land
    -0.06
    ity
    -0.06
    hein
    -0.06
    !
    -0.06
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.06
    –
    -0.05
    *
    -0.05
    POSITIVE LOGITS
     apprezz
    0.09
    çĶŁç´ł
    0.08
    精确
    0.08
    uwen
    0.08
    ROTO
    0.08
    блÑİ
    0.08
    rebs
    0.08
    åħ¥éĩij
    0.08
    arana
    0.08
    adero
    0.07
    Activations Density 0.000%

    No Known Activations