© 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. 2650
    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
    omag
    -0.07
     Lab
    -0.06
     lab
    -0.06
    IRD
    -0.06
     Mach
    -0.06
    atur
    -0.06
     no
    -0.06
    arton
    -0.05
    奥
    -0.05
    é¦
    -0.05
    POSITIVE LOGITS
    伯çĪµ
    0.08
    åħ¨éĿ¢åĬłå¼º
    0.08
    teros
    0.08
    éĤ£æ®µ
    0.08
    alh
    0.08
     pozor
    0.08
    ç¨
    0.08
    bour
    0.08
    essos
    0.08
    ุà¸ĩ
    0.08
    Activations Density 0.000%

    No Known Activations