© 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. 30324
    Prev
    Next
    INDEX
    Explanations

    true or false evaluation

    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
    enor
    -0.09
     Maur
    -0.07
    венÑĮ
    -0.07
    解éļ¾
    -0.06
    ToOne
    -0.06
    æĪijç»Ļä½ł
    -0.06
    agal
    -0.06
     resultant
    -0.06
    cp
    -0.06
    glich
    -0.06
    POSITIVE LOGITS
    info
    0.07
    URED
    0.07
    лана
    0.07
    roids
    0.07
    çIJ
    0.07
    ÃŃos
    0.07
    rochen
    0.07
    æ¯ĭ庸置çĸij
    0.07
    olen
    0.07
    rå
    0.07
    Activations Density 0.001%

    No Known Activations