© 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. 22879
    Prev
    Next
    INDEX
    Explanations

    whitespace characters, particularly newlines and tabs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     âĢ¦
    -0.07
    å¥½å¥½åľ°
    -0.07
    åıĬæľīåħ³
    -0.07
    ç´§ç´§åľ°
    -0.07
    é«ĺçŃīåŃ¦æł¡
    -0.06
    欢è¿İ大家éĺħ读
    -0.06
    éĿŀ常çļĦ
    -0.06
    æĮīçħ§åĽ½å®¶
    -0.06
    -0.06
    æĽ´åĬłçļĦ
    -0.06
    POSITIVE LOGITS
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.09
    èµŀè¿ĩ
    0.08
    æĭĨ解
    0.08
    è¯Ħä»·ä½ĵç³»
    0.08
    è¶ħé¢ĦæľŁ
    0.08
    çĹĩæĤ£èĢħ
    0.07
    åĨįéĢł
    0.07
     übrigens
    0.07
    èĭ¦ç¬ij
    0.07
    é¢ĦåĪ¤
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.