© 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. 27021
    Prev
    Next
    INDEX
    Explanations

    consecutive

    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
    çįĦ
    -0.08
    izr
    -0.07
    åĪ°è´§
    -0.07
    åĪ©æ¶¦çİĩ
    -0.07
    akest
    -0.07
    รุà¹Īà¸Ļ
    -0.07
    å¿ĹåĪļ
    -0.06
     Subset
    -0.06
     Blur
    -0.06
    ä¼ļéķ¿
    -0.06
    POSITIVE LOGITS
    åľ¨è§Ħå®ļæŶéĹ´åĨħ
    0.09
    å¿ħé¡»åħĪ
    0.09
     valid
    0.08
    ä¸įå¾Ĺ以任ä½ķ
    0.08
    ä¸įèĥ½ä½ľä¸º
    0.08
     Invalid
    0.08
     consecutive
    0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
    æľīä¸ĭåĪĹ
    0.08
    å¿ħé¡»è¿Ľè¡Į
    0.08
    Activations Density 0.029%

    No Known Activations