© 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. 27591
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and percentages

    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
     jedin
    -0.08
    ê°Ī
    -0.08
    ç¼¥ç¼Ī
    -0.07
    orce
    -0.07
    akit
    -0.07
    chinen
    -0.07
     Ðķдин
    -0.07
    _special
    -0.07
    wód
    -0.07
    åĬłåĭĴ
    -0.07
    POSITIVE LOGITS
    åŁºæķ°
    0.09
    uve
    0.08
    ahren
    0.07
    çĪ±æĥľ
    0.07
     preval
    0.06
    idon
    0.06
    å¾Ģå¤ĸ
    0.06
    åѦçĶŁ
    0.06
    ä¸Ĭ空
    0.06
     Sut
    0.06
    Activations Density 0.031%

    No Known Activations