© 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. 31166
    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
    åĩºèµĦæ¯Ķä¾ĭ
    -0.07
    adel
    -0.07
    人æķ°
    -0.07
    åħ·æľīçĭ¬ç«ĭ
    -0.07
    æĮ¯åįİ
    -0.06
    apel
    -0.06
    å¨ģåĬĽ
    -0.06
    acle
    -0.06
    aset
    -0.06
    tero
    -0.06
    POSITIVE LOGITS
    gross
    0.08
    æ¯ıåħ¬æĸ¤
    0.08
     priv
    0.08
     calor
    0.08
    åį§
    0.08
    states
    0.07
    ä¸įæĸŃæĽ´æĸ°
    0.07
     datum
    0.07
    वान
    0.07
    ä»ĩ
    0.07
    Activations Density 0.000%

    No Known Activations