© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32133
    Prev
    Next
    INDEX
    Explanations

    syntax and parsing

    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
    szcz
    -0.08
    ä»
    -0.08
    微信æī«çłģ
    -0.08
    æľªæĿ¥åıijå±ķ
    -0.07
    zcz
    -0.07
    uches
    -0.07
    eut
    -0.07
    alarm
    -0.07
     alarm
    -0.07
    èī¯åĵģ
    -0.07
    POSITIVE LOGITS
    ç»ijæŀ¶
    0.08
    鼷鼨
    0.07
    å±Ĥå±Ĥ
    0.07
    çĭ¸
    0.07
    aptor
    0.07
     lexical
    0.07
    å±Ĥ级
    0.07
    igm
    0.07
     syntax
    0.07
     parsing
    0.07
    Activations Density 0.011%

    No Known Activations