© 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. 33140
    Prev
    Next
    INDEX
    Explanations

    date ranges

    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
    ä¸ĭä¸ĢæŃ¥
    -0.08
    åĴ«å°º
    -0.07
    å±ĬæŶ
    -0.07
    åįĥ亿
    -0.07
    å½ĵæĻļ
    -0.07
     helic
    -0.07
    å½ĵ天ä¸ĭåįĪ
    -0.07
    å½ĵ天çļĦ
    -0.06
    åĩłåĪĨéĴŁ
    -0.06
     loc
    -0.06
    POSITIVE LOGITS
     period
    0.10
     Zeitraum
    0.09
     periods
    0.09
     years
    0.09
    æľŁéĹ´
    0.09
    ãĤĴ対象
    0.08
    periode
    0.08
    涵çĽĸ
    0.08
     기ê°Ħ
    0.08
    æľŁéĸĵ
    0.08
    Activations Density 0.425%

    No Known Activations