© 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. 14592
    Prev
    Next
    INDEX
    Explanations

    growth and transition

    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
    çªģåĩ»
    -0.07
    Bone
    -0.06
    bone
    -0.06
    peg
    -0.06
     immutable
    -0.06
    çĴŁ
    -0.06
    fort
    -0.06
    çħ§
    -0.06
    æĢĢ
    -0.06
    çĶ¨åľ¨
    -0.06
    POSITIVE LOGITS
     formations
    0.11
     formation
    0.11
    éĶ¦æ¶Ľ
    0.09
     Formation
    0.09
    并形æĪIJ
    0.09
    å½¢æĪIJä¸Ģ个
    0.09
    主ä½ĵç»ĵæŀĦ
    0.09
     ÑĦоÑĢмиÑĢÑĥеÑĤÑģÑı
    0.09
     ÑĦоÑĢмиÑĢование
    0.08
    åıijå±ķæĪIJ
    0.08
    Activations Density 0.060%

    No Known Activations