© 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. 12440
    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
    ght
    -0.07
    åı¯çĶ³è¯·
    -0.07
    ÑħÑĤа
    -0.07
    æľī为
    -0.07
    åĴĮäºĮ
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    为åİŁåĪĻ
    -0.07
    为éĺ²æŃ¢
    -0.07
    æłĩéħį
    -0.06
    utow
    -0.06
    POSITIVE LOGITS
    离线
    0.07
    ä»£æĽ¿
    0.07
    åħ¹
    0.07
    zte
    0.07
    rar
    0.07
     asn
    0.07
    tras
    0.06
    isman
    0.06
     CONTRIBUTORS
    0.06
    è¿Ļ份
    0.06
    Activations Density 0.000%

    No Known Activations