© 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. 32068
    Prev
    Next
    INDEX
    Explanations

    replication, copies, duplication

    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
    æĬĬ人
    -0.07
     Save
    -0.07
     general
    -0.06
    éļıæīĭ
    -0.06
     generic
    -0.06
    ç²¾éĢī
    -0.06
    antie
    -0.06
    play
    -0.06
     Supply
    -0.06
    è¿Ľäº¬
    -0.06
    POSITIVE LOGITS
    /original
    0.11
     replication
    0.10
    åİŁä»¶
    0.09
    å®Įæķ´
    0.09
    åī¯æľ¬
    0.09
     copies
    0.09
    -original
    0.09
    -new
    0.09
    æĸ°çĶŁçļĦ
    0.09
    å¤įåĪ¶
    0.09
    Activations Density 0.003%

    No Known Activations