© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62511
    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
    éĽĨéĶ¦
    -0.07
     поÑģÑĥ
    -0.07
    quip
    -0.07
    mano
    -0.07
    åģļä¸įåĪ°
    -0.06
    éļĬ
    -0.06
     conduct
    -0.06
    è°§
    -0.06
    émy
    -0.06
    ç¬Ļ
    -0.06
    POSITIVE LOGITS
    ansi
    0.08
     preceding
    0.08
    azah
    0.07
    åıĬ以ä¸ĭ
    0.07
    æīĢå±ŀ
    0.07
    æľªæ»¡
    0.07
    reserve
    0.07
    è¿ĺåĮħæĭ¬
    0.07
     tartal
    0.07
    æŀĦæĪIJ
    0.07
    Activations Density 0.000%

    No Known Activations