© 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. 10636
    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
    åį«çĶŁç»Ħç»ĩ
    -0.09
    ccoli
    -0.08
    mtree
    -0.08
    使èĩªå·±
    -0.08
    anine
    -0.07
    ets
    -0.07
    æ¯Ķèµ·æĿ¥
    -0.07
    áĥłáĥIJ
    -0.07
    شتÙĩ
    -0.07
    rvine
    -0.07
    POSITIVE LOGITS
    éĩįå¤į
    0.07
     repetitive
    0.07
    ä¾Ŀ次
    0.06
    éĩįè¤ĩ
    0.06
    å¼ĢåĪ°
    0.06
    æĹł
    0.06
    龸
    0.06
    asm
    0.06
    -repeat
    0.06
    æĸľ
    0.06
    Activations Density 0.000%

    No Known Activations