© 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. 60910
    Prev
    Next
    INDEX
    Explanations

    qualities or degrees

    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
    æľĢç¾İçļĦ
    -0.07
    æľĢæľĢ
    -0.07
     destined
    -0.06
    asitas
    -0.06
    ÑĩаÑı
    -0.06
    åįģåħ¨
    -0.06
    åı¯çĸij
    -0.06
    uple
    -0.06
    èĦ±èIJ½
    -0.06
     destiny
    -0.06
    POSITIVE LOGITS
     lack
    0.14
    lack
    0.11
     absence
    0.11
     presence
    0.10
    çī¹æľīçļĦ
    0.10
     Lack
    0.10
    absence
    0.09
    åĽºæľīçļĦ
    0.09
    çĭ¬çī¹çļĦ
    0.09
     inherent
    0.08
    Activations Density 0.463%

    No Known Activations