© 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. 65065
    Prev
    Next
    INDEX
    Explanations

    adaptation and transformation

    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
     anomal
    -0.06
    浸
    -0.06
    èĩªåĬ¨
    -0.06
     esco
    -0.06
    .directory
    -0.06
    uan
    -0.06
    AUTO
    -0.06
     asc
    -0.06
    æ£ĺ
    -0.06
    -supported
    -0.06
    POSITIVE LOGITS
     reinterpret
    0.13
    以éĢĤåºĶ
    0.13
    ãĤ¢ãĥ¬ãĥ³ãĤ¸
    0.12
    æĶ¹ç¼ĸ
    0.12
     adaptation
    0.11
     adapting
    0.11
     tweaked
    0.10
    reinterpret
    0.10
    éĢĤåºĶ
    0.10
     адапÑĤи
    0.10
    Activations Density 0.149%

    No Known Activations