© 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. 22891
    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
    æĹłå£°
    -0.06
    PROTO
    -0.06
    agner
    -0.06
    ä¸įæĪIJ
    -0.06
    leter
    -0.06
    çĬ¹
    -0.06
    иа
    -0.06
     Broadway
    -0.06
    趾
    -0.06
    æĬµ
    -0.06
    POSITIVE LOGITS
    ä¸ŃåĽ½å®¶
    0.08
    éij½
    0.08
    äºİè¡Į
    0.07
    .bz
    0.07
    å¨ĵ
    0.07
    çĸ
    0.07
    Ĭ
    0.07
    hon
    0.07
    åħ·æľī以ä¸ĭ
    0.07
     Kunde
    0.07
    Activations Density 0.000%

    No Known Activations