© 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. 64213
    Prev
    Next
    INDEX
    Explanations

    sequence iui?

    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
    LIO
    -0.07
    ä¸Ģéĥİ
    -0.07
    ug
    -0.07
     best
    -0.06
     prom
    -0.06
    çĶµåŃIJçīĪ
    -0.06
    ugn
    -0.06
    kli
    -0.06
     Buyers
    -0.06
    çĶµåŃIJåķĨåĬ¡æľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    Ī
    0.08
    å®
    0.07
     mote
    0.07
    为è¾ħ
    0.07
     ($.
    0.07
    ä¸ĩèĥ½
    0.07
     Crosby
    0.07
    ä¸ĩåıª
    0.06
    _RESOLUTION
    0.06
    ķĮ
    0.06
    Activations Density 0.012%

    No Known Activations