© 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. 49178
    Prev
    Next
    INDEX
    Explanations

    is or 's followed by a word

    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
    Not in Any Lists

    No Comments

    Negative Logits
    uktion
    -0.08
    бÑĥдÑĮ
    -0.07
    è¿Ļæĺ¯çĶ±äºİ
    -0.07
    akedown
    -0.07
    æŁIJäºĽ
    -0.07
    éĤ£æĺ¯åĽłä¸º
    -0.07
    utdown
    -0.07
    ationship
    -0.07
    urbed
    -0.07
    orang
    -0.07
    POSITIVE LOGITS
     اÙĦبتÙĩ
    0.07
    类似äºİ
    0.07
    пÑĢоÑĩем
    0.07
    è°ĵ
    0.07
    полни
    0.07
     certainly
    0.07
    éĢļ常
    0.07
    çĭĹä»Ķ
    0.06
    av
    0.06
    åħĪå¾Ĺ
    0.06
    Activations Density 0.015%

    No Known Activations