© 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. 64894
    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
    éļħ
    -0.07
    éķĩéķ¿
    -0.06
     scand
    -0.06
     óleo
    -0.06
    çĴ
    -0.06
     chừng
    -0.06
    oot
    -0.06
    ç¼Ī
    -0.06
    arc
    -0.06
    ansi
    -0.06
    POSITIVE LOGITS
    prites
    0.08
    cha
    0.08
    æ®ĭ
    0.08
    æĬĺ
    0.07
    æ®ĺ
    0.07
    Ïģαι
    0.07
    夷
    0.07
    åı¯æĮī
    0.07
    å¨ľå¨ľ
    0.07
    vertime
    0.07
    Activations Density 0.000%

    No Known Activations