© 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. 30468
    Prev
    Next
    INDEX
    Explanations

    scaling, proportional, dose, concentration, measurements

    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
    asten
    -0.09
    -navigation
    -0.07
    .circular
    -0.07
    æ°Ľ
    -0.06
     arcs
    -0.06
    åºĵ
    -0.06
    ä¸ĢéĢļ
    -0.06
    (hex
    -0.06
     prom
    -0.06
    ENDA
    -0.06
    POSITIVE LOGITS
     scaling
    0.10
     proportional
    0.10
     Scaling
    0.09
    Scaling
    0.09
    åĢįæķ°
    0.09
    scaling
    0.09
    scaled
    0.09
     scaled
    0.08
    线æĢ§
    0.08
    å¢ŀåĬł
    0.08
    Activations Density 0.018%

    No Known Activations