© 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. 23227
    Prev
    Next
    INDEX
    Explanations

    market for financial discussions

    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
    atel
    -0.08
    /disable
    -0.08
    zelf
    -0.08
    ormais
    -0.08
    ê¼
    -0.08
    heim
    -0.08
    enso
    -0.08
    estan
    -0.08
    enia
    -0.07
    /el
    -0.07
    POSITIVE LOGITS
    places
    0.12
     ÑģбÑĭ
    0.11
    à¸Ļัà¸Ķ
    0.09
    place
    0.07
    illing
    0.07
    -facing
    0.07
    åĴĮå¸Ĥåľº
    0.07
    ization
    0.07
    åĴĮ产åĵģ
    0.07
    åį«çĶŁç»Ħç»ĩ
    0.07
    Activations Density 0.041%

    No Known Activations