© 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. 32967
    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
    awat
    -0.08
    alloc
    -0.08
    çĦ¶æĺ¯
    -0.08
    hren
    -0.07
    olvable
    -0.07
     Guten
    -0.07
    osz
    -0.07
    onos
    -0.07
    è¿Ľä¸ĢæŃ¥æī©å¤§
    -0.07
    åĪ©çī©
    -0.07
    POSITIVE LOGITS
    iaus
    0.07
    驱
    0.07
    erk
    0.06
    æ¸
    0.06
     Fi
    0.06
    å¡ĺéķĩ
    0.06
    âĦ¢
    0.06
    èĩ´
    0.05
    éĢļãĤĬ
    0.05
     Ấ
    0.05
    Activations Density 0.000%

    No Known Activations