© 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. 33014
    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
    Âł
    -0.08
     legal
    -0.06
    æ´»
    -0.06
    å¾ĭ
    -0.06
    å§Ķ
    -0.06
    odes
    -0.06
    èį¯
    -0.06
    ...
    -0.06
    å®Ŀ
    -0.06
    å®Ī
    -0.06
    POSITIVE LOGITS
    ardini
    0.09
    æĦŁè¨Ģ
    0.08
    ockey
    0.08
    trate
    0.08
    beginn
    0.08
     posteri
    0.08
    XP
    0.08
     Thao
    0.08
    æŁ¥çľĭåħ¨éĥ¨
    0.08
    ansch
    0.08
    Activations Density 0.000%

    No Known Activations