© 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. 8580
    Prev
    Next
    INDEX
    Explanations

    replication

    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
    _framework
    -0.08
    ozo
    -0.08
    æīĢ欲
    -0.07
    reon
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
    ingend
    -0.07
    edList
    -0.07
    ARC
    -0.07
    andy
    -0.07
    ÑĢики
    -0.07
    POSITIVE LOGITS
    prov
    0.07
    å¤įåĪ¶
    0.07
    çĿĽ
    0.07
     replic
    0.07
    itten
    0.07
    éĩįå¤į
    0.07
     replicate
    0.07
     replication
    0.07
     replicated
    0.07
     повÑĤоÑĢÑı
    0.07
    Activations Density 0.001%

    No Known Activations