© 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. 63733
    Prev
    Next
    INDEX
    Explanations

    smaller, higher, increases, decreases

    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
    aktu
    -0.07
     Integrity
    -0.07
    çī¹æ®ĬçļĦ
    -0.07
    idy
    -0.07
     integrity
    -0.07
    èªĵ
    -0.07
     reparto
    -0.07
    ä¸įæŀĦæĪIJ
    -0.07
    å®Įæķ´çļĦ
    -0.07
    _SYNC
    -0.07
    POSITIVE LOGITS
     invers
    0.12
     ÙĥÙĦÙħا
    0.12
    è¶Ĭé«ĺ
    0.12
    è¶Ĭ大
    0.12
    è¶Ĭ
    0.12
    æĦĪ
    0.12
     Semakin
    0.11
     semakin
    0.11
     ยิà¹Īà¸ĩ
    0.11
     decreases
    0.11
    Activations Density 0.146%

    No Known Activations