© 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. 41328
    Prev
    Next
    INDEX
    Explanations

    dimensions and hardware specifications

    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
    éĥ¨ä»½
    -0.08
    ازÙĦ
    -0.08
    /do
    -0.08
    .asc
    -0.08
    绪
    -0.07
    Style
    -0.07
    çĪ±å²Ĺ
    -0.07
    indered
    -0.07
    ufer
    -0.07
    νεÏĤ
    -0.07
    POSITIVE LOGITS
    +
    0.08
     itself
    0.07
     minus
    0.07
    æľ¬èº«
    0.06
     Nego
    0.06
     hoped
    0.06
     plus
    0.06
    `
    0.06
    alz
    0.06
     +
    0.06
    Activations Density 0.027%

    No Known Activations