© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
     sol
    -0.06
    åĩºçº³
    -0.06
     ter
    -0.06
     set
    -0.05
    corn
    -0.05
     [âĢ¦]
    -0.05
     bre
    -0.05
    âĢ¦
    -0.05
     reb
    -0.05
    åħĨ
    -0.05
    POSITIVE LOGITS
    esch
    0.08
    kab
    0.08
    emy
    0.08
    пÑĸ
    0.08
    æī«çłģåħ³æ³¨
    0.08
    жеÑĤ
    0.08
     دعا
    0.08
    微信æī«çłģ
    0.08
    olley
    0.08
    .ws
    0.08
    Activations Density 0.001%

    No Known Activations