© 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. 48156
    Prev
    Next
    INDEX
    Explanations

    qualities, traits, talents, abilities

    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
    pruch
    -0.08
    大æĪı
    -0.07
    ãĥŃãĥĥ
    -0.07
     Vorg
    -0.07
    ãĥĹãĥ©ãĤ¤
    -0.07
    egram
    -0.07
     sensitive
    -0.07
     Chore
    -0.07
    ä¸Ģåıij
    -0.07
     proceedings
    -0.07
    POSITIVE LOGITS
     qualities
    0.12
     traits
    0.11
     abilities
    0.11
     dimiliki
    0.10
     talent
    0.10
     talents
    0.10
     charisma
    0.10
     ability
    0.10
     attributes
    0.09
    åĩºä¼Ĺ
    0.09
    Activations Density 0.134%

    No Known Activations