© 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. 8047
    Prev
    Next
    INDEX
    Explanations

    hierarchical tree structures

    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
    heb
    -0.06
    åħį
    -0.06
    çªĹåı£
    -0.06
    tool
    -0.06
    vang
    -0.06
    uler
    -0.06
     AS
    -0.05
    ç©¿è¶Ĭ
    -0.05
    è¿ŀç»Ń
    -0.05
    áĢ¶
    -0.05
    POSITIVE LOGITS
     subtree
    0.15
     recursively
    0.13
     nested
    0.13
     subdivisions
    0.13
    nested
    0.13
    åµĮå¥Ĺ
    0.12
    å±Ĥ级
    0.12
    éĢĴå½Ĵ
    0.12
    æłij
    0.12
     hierarchical
    0.12
    Activations Density 0.371%

    No Known Activations