© 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. 43192
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    Äģm
    -0.08
    æºĸ
    -0.08
    çģ°çĥ¬
    -0.07
    arro
    -0.07
    cez
    -0.07
    irme
    -0.06
    è¿ľçļĦ
    -0.06
     protected
    -0.06
    æľ¬ç½ij
    -0.06
    è¯ķè¯ķåIJ§
    -0.06
    POSITIVE LOGITS
    uling
    0.06
     cant
    0.06
    èĩªå·±çļĦçĶŁåij½
    0.06
    iffer
    0.06
    åħ°çī¹
    0.06
    illage
    0.06
    éģĩ
    0.06
    elten
    0.06
    ãģ¾ãģĽãĤĵãģĭ
    0.06
    è¯įåħ¸
    0.06
    Activations Density 0.002%

    No Known Activations