© 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. 19034
    Prev
    Next
    INDEX
    Explanations

    recursive depth-first search paths

    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
    èĢĺ
    -0.07
    Metro
    -0.06
    容éĩıçļĦ
    -0.06
    åģıå¿ĥ
    -0.06
     vend
    -0.06
    çļĦ人æĢ§
    -0.06
     Faro
    -0.06
    éļĻ
    -0.06
    adera
    -0.06
    رع
    -0.06
    POSITIVE LOGITS
    spath
    0.08
    dfs
    0.08
     Paths
    0.08
     paths
    0.08
    æļĤ
    0.08
    odings
    0.08
     backtrack
    0.08
     diak
    0.07
    ZION
    0.07
     DFS
    0.07
    Activations Density 0.020%

    No Known Activations