© 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. 46909
    Prev
    Next
    INDEX
    Explanations

    node data 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
    éľĵ
    -0.08
     VARIABLES
    -0.08
    -inline
    -0.08
     Mitar
    -0.07
     variables
    -0.07
     Err
    -0.07
    variables
    -0.07
    /pm
    -0.07
    ä¹ĸå·§
    -0.07
    bruar
    -0.07
    POSITIVE LOGITS
    çłĶ究æīĢæīĢéķ¿
    0.07
    æ°ij主
    0.07
    .Identifier
    0.06
    kho
    0.06
     surrounded
    0.06
    .center
    0.06
    æīĵåį°
    0.06
    éĿ¢æľĿ
    0.06
    å®Įæķ´
    0.06
    stä
    0.06
    Activations Density 0.046%

    No Known Activations