© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 63955
    Prev
    Next
    INDEX
    Explanations

    Looking at the activations, I notice that all activation values are 0 across all the examples provided. This neuron does not activate for any of the tokens shown. The neuron appears to be **inactive or not finding its target pattern in these documents**.

    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
    好åĥı
    -0.09
    å¾Īæľī
    -0.09
     realtime
    -0.08
     ancest
    -0.08
    ηÏĥη
    -0.08
     bigger
    -0.08
    Âł
    -0.08
     ÂŃ
    -0.08
    åºĶ该
    -0.08
    è¡£æľįçļĦ
    -0.08
    POSITIVE LOGITS
    ä»įå¤Ħäºİ
    0.08
    便å°Ĩ
    0.08
     **
    0.07
    Õ§
    0.07
    ä¸Ĭåįĩèĩ³
    0.07
    ä¹Łå¹¶éĿŀ
    0.07
    åį³åı¯å®ĮæĪIJ
    0.07
     $
    0.07
    å°ıç¼ĸ为大家
    0.06
    æĸ¹æīį
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.