© 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. 10798
    Prev
    Next
    INDEX
    Explanations

    roots of quadratic equation

    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
    ä¸īèĢħ
    -0.08
    åħ¶ä»ĸ人çļĦ
    -0.07
    å°½èģĮ尽责
    -0.07
    assis
    -0.07
    igo
    -0.06
    scratch
    -0.06
    Ïĥι
    -0.06
    eth
    -0.06
    itto
    -0.06
    mano
    -0.06
    POSITIVE LOGITS
    第ä¸Ģæī¹
    0.08
    ùy
    0.08
    åĪĨåĪ«ä¸º
    0.08
     nghiá»ĩm
    0.08
    两大类
    0.08
    åIJĦèĩªçļĦ
    0.08
    ä¹ĭä¸ĢçļĦ
    0.08
    åħ¶ä¸Ńä¸Ģ个
    0.07
    è½®æµģ
    0.07
    ä¹ĭäºĮ
    0.07
    Activations Density 0.003%

    No Known Activations