© 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. 16875
    Prev
    Next
    INDEX
    Explanations

    beans, soy, legumes

    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
    atten
    -0.09
    indel
    -0.08
    isbury
    -0.08
    hong
    -0.07
     caut
    -0.07
    quita
    -0.07
    åĴĮèĥ½åĬĽ
    -0.07
    Pokemon
    -0.07
     PRESID
    -0.07
    reature
    -0.07
    POSITIVE LOGITS
    beans
    0.10
    bean
    0.10
     bean
    0.09
    èĶ»
    0.08
     beans
    0.08
    大è±Ĩ
    0.08
    èĬ¸
    0.08
     Carnegie
    0.08
     Bean
    0.08
    åıijèĬ½
    0.08
    Activations Density 0.043%

    No Known Activations