© 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. 12790
    Prev
    Next
    INDEX
    Explanations

    factuality or being known

    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
    åıªè¦ģèĥ½
    -0.08
    åıªè¦ģæľī
    -0.07
    imed
    -0.07
    _suite
    -0.07
    HCI
    -0.06
    zij
    -0.06
    ิà¹Īà¸ĩ
    -0.06
     Definitions
    -0.06
    缴æĮĩ
    -0.06
    åĪĨå¤ĸ
    -0.06
    POSITIVE LOGITS
     known
    0.11
    -known
    0.11
    Known
    0.10
     Known
    0.10
    æĪijçŁ¥éģĵ
    0.10
    _known
    0.10
     bekannt
    0.10
     reportedly
    0.10
    known
    0.10
    åħ¬è®¤çļĦ
    0.10
    Activations Density 0.017%

    No Known Activations