© 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. 63422
    Prev
    Next
    INDEX
    Explanations

    deeply nested recursive merging

    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
    ehr
    -0.08
    лок
    -0.08
    eram
    -0.08
    øre
    -0.07
    Configurer
    -0.07
     thá»ķ
    -0.07
    oyer
    -0.07
    tek
    -0.07
    ock
    -0.07
    åįĬè¾¹
    -0.07
    POSITIVE LOGITS
     recursively
    0.15
    éĢĴå½Ĵ
    0.15
    åµĮå¥Ĺ
    0.14
    recursive
    0.13
     nested
    0.13
     recursive
    0.13
    nested
    0.13
     nesting
    0.13
    Recursive
    0.12
    å±Ĥ级
    0.12
    Activations Density 0.236%

    No Known Activations