© 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. 43896
    Prev
    Next
    INDEX
    Explanations

    anthropomorphic, sentient, intelligent beings

    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
    寸
    -0.08
    oked
    -0.07
    ogl
    -0.07
    ket
    -0.07
     casse
    -0.07
    elib
    -0.07
    aunch
    -0.07
    istri
    -0.07
    åħĭ森
    -0.06
    æĹ©
    -0.06
    POSITIVE LOGITS
    人类çļĦ
    0.11
     sentient
    0.10
     humans
    0.10
    èĥ½åĬ¨
    0.10
     human
    0.10
    èµĭäºĪäºĨ
    0.10
    人类
    0.10
    èµĭäºĪ
    0.10
    æĺ¯äººç±»
    0.10
     humano
    0.09
    Activations Density 0.040%

    No Known Activations