© 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. 41563
    Prev
    Next
    INDEX
    Explanations

    heavy metal or petroleum products

    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
    lee
    -0.07
     either
    -0.07
    çŃīåŁºæľ¬
    -0.07
    ahir
    -0.07
    ajar
    -0.07
    ä¸Ĭä¸ĭ
    -0.07
    èĶ·
    -0.07
    chy
    -0.06
    either
    -0.06
    天ä¸ĭ
    -0.06
    POSITIVE LOGITS
    alytics
    0.08
    ìĪĺë¡Ŀ
    0.08
     импоÑĢÑĤ
    0.07
    å¤įæĿĤçļĦ
    0.07
     (>
    0.07
    å¤įæĿĤ度
    0.07
    åľ°åĮºçļĦ
    0.07
    .getElementsByName
    0.07
    주기
    0.07
    inki
    0.07
    Activations Density 0.004%

    No Known Activations