© 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. 46647
    Prev
    Next
    INDEX
    Explanations

    false positive rates

    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
    apis
    -0.07
    çĪ¶åŃIJ
    -0.07
     Bless
    -0.06
     momentarily
    -0.06
    literal
    -0.06
    åıĤä¸İåħ¶ä¸Ń
    -0.06
    Name
    -0.06
    åįķä¸ĢçļĦ
    -0.06
    umm
    -0.06
    layout
    -0.06
    POSITIVE LOGITS
     falsely
    0.09
    ADV
    0.08
    æ²ŁæĿij
    0.08
    orex
    0.08
    _INCLUDED
    0.08
    åı°å±±
    0.08
    chado
    0.08
     обÑģлед
    0.07
    faker
    0.07
     вовÑĢемÑı
    0.07
    Activations Density 0.023%

    No Known Activations