© 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. 16182
    Prev
    Next
    INDEX
    Explanations

    public defender and institute

    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
    ysel
    -0.07
     ìķĦëĭĪê³ł
    -0.07
    _GEN
    -0.07
    ãģĵãģ¨ãĤĦ
    -0.07
    antik
    -0.07
    anty
    -0.07
    aghan
    -0.07
    даниÑı
    -0.07
    ancia
    -0.07
    çļ®åħ·
    -0.07
    POSITIVE LOGITS
    两èĢħ
    0.14
    äºĮèĢħ
    0.13
    ãģ©ãģ¡ãĤīãĤĤ
    0.12
    è¿ĻäºĽéĥ½æĺ¯
    0.12
    è¿Ļ两
    0.11
    åħ©èĢħ
    0.11
    ãģĿãĤĮãģŀãĤĮ
    0.11
    ãģĦãģļãĤĮ
    0.10
     ambas
    0.10
     ambos
    0.10
    Activations Density 0.415%

    No Known Activations