© 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. 28181
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes

    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
    idon
    -0.08
    Õ¸Õ²
    -0.07
    unde
    -0.07
    zte
    -0.07
    èīºæľ¯ç±»
    -0.07
    tmpl
    -0.07
    ç±»åĴĮ
    -0.07
    éĩij鸡
    -0.07
    è¿Ļç±»
    -0.06
    zis
    -0.06
    POSITIVE LOGITS
    agar
    0.08
    bucks
    0.07
    åĪĻåľ¨
    0.07
    åĪĻ为
    0.07
    åĪĻ
    0.07
    çĻ¾å²ģ
    0.07
     forms
    0.07
     Monza
    0.07
    婦
    0.07
    baut
    0.07
    Activations Density 0.439%

    No Known Activations