© 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. 16569
    Prev
    Next
    INDEX
    Explanations

    field theory concepts

    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
     Seger
    -0.08
    人æ°ijåħ±åĴĮåĽ½
    -0.08
    ymar
    -0.08
     صادر
    -0.08
    andle
    -0.08
    å¸ĥå°Ķ
    -0.08
    vro
    -0.08
    çĤ¬
    -0.07
    lanz
    -0.07
    .Raw
    -0.07
    POSITIVE LOGITS
     effects
    0.08
    å·£
    0.08
    çݯå¢ĥå½±åĵį
    0.07
     corrections
    0.07
     etk
    0.07
     loops
    0.07
     Effects
    0.07
    umerator
    0.07
     contributions
    0.07
    effects
    0.07
    Activations Density 0.014%

    No Known Activations