© 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. 61049
    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
    åħ·ä½ĵæĿ¥è¯´
    -0.06
     [âĢ¦]
    -0.06
     (
    -0.06
    unden
    -0.06
    “
    -0.06
    ...",
    -0.06
    ä»Ķ
    -0.05
    ä¼ļ
    -0.05
    ï¼Ī
    -0.05
     monte
    -0.05
    POSITIVE LOGITS
    halen
    0.09
    缸åħ³éĹ®çŃĶ
    0.09
    rokes
    0.09
    juta
    0.08
    abox
    0.08
    lande
    0.08
     ÐķÑģÑĤе
    0.08
    볨
    0.08
    roke
    0.08
    æĽ´å¤ļåĨħ容
    0.08
    Activations Density 0.000%

    No Known Activations