© 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. 18033
    Prev
    Next
    INDEX
    Explanations

    relative and comparative

    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
    تب
    -0.07
    .dot
    -0.07
    éģµå®ĪåĽ½å®¶
    -0.07
    ays
    -0.06
    _filters
    -0.06
    毫ä¸į
    -0.06
    èĩªçĦ¶äºº
    -0.06
    æĩ
    -0.06
    มูล
    -0.06
    è¾Ľ
    -0.06
    POSITIVE LOGITS
     relative
    0.20
    çĽ¸å¯¹æ¯Ķè¾ĥ
    0.20
    Relative
    0.19
    relative
    0.19
     Relative
    0.18
    çĽ¸å¯¹
    0.17
    -relative
    0.17
    .relative
    0.17
     comparative
    0.16
    çĽ¸å¯¹èĢĮè¨Ģ
    0.16
    Activations Density 0.103%

    No Known Activations