© 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. 11594
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with which

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    uyo
    -0.08
    çļĦ人æ°ij
    -0.06
    ugat
    -0.06
    å®ĥå°±æĺ¯
    -0.06
    èµ·
    -0.06
    dog
    -0.06
    让åŃ©åŃIJ们
    -0.06
    žite
    -0.06
     Marxism
    -0.06
     statewide
    -0.06
    POSITIVE LOGITS
    åıĮæĸ¹åľ¨
    0.10
    åħ¬åı¸å°Ĩ
    0.10
    ä½ľèĢħåľ¨
    0.09
    çĶ¨æĪ·åľ¨
    0.09
    åħ¬åı¸ä»¥
    0.09
     pihaknya
    0.08
     isteyen
    0.08
    åıĮæĸ¹
    0.08
    åįļ主
    0.08
    åħ¬åı¸åľ¨
    0.08
    Activations Density 0.841%

    No Known Activations