© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8793
    Prev
    Next
    INDEX
    Explanations

    changing or replacing text

    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
    ola
    -0.08
    ä½ĨéļıçĿĢ
    -0.08
    erb
    -0.08
     Junk
    -0.07
    oins
    -0.07
    úd
    -0.07
    à¹Ĥà¸ĭ
    -0.07
    çĬ
    -0.07
    ëģĦ
    -0.07
    appendTo
    -0.07
    POSITIVE LOGITS
     substitution
    0.08
     substitutions
    0.08
    转åĮĸ
    0.08
     wherever
    0.08
     replacements
    0.07
    upas
    0.07
    åĩ¡æĺ¯
    0.07
    /remove
    0.07
     substituted
    0.07
    conversion
    0.07
    Activations Density 0.002%

    No Known Activations