© 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. 10406
    Prev
    Next
    INDEX
    Explanations

    IEEE publications

    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
    phy
    -0.09
    thouse
    -0.08
    ä¸įæķ£
    -0.08
    éĢ²åı£
    -0.07
    alach
    -0.07
    dam
    -0.07
    -API
    -0.07
    cola
    -0.07
     dejo
    -0.07
    มั
    -0.07
    POSITIVE LOGITS
     IEEE
    0.09
    IEEE
    0.09
    çĶµæ°Ķ设å¤ĩ
    0.08
    ä¾ĽçĶµ
    0.07
    ITU
    0.07
    åĬŁçİĩ
    0.07
    ÏĮν
    0.07
    çĶµèĥ½
    0.07
    ouro
    0.07
     ìłĦìĽIJ
    0.07
    Activations Density 0.017%

    No Known Activations