© 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. 22174
    Prev
    Next
    INDEX
    Explanations

    rugby league footballer

    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
    èĭĩ
    -0.06
    éĢļ
    -0.06
     either
    -0.06
    åħ¶æīĢ
    -0.06
    线ä¸Ĭ
    -0.06
    Ap
    -0.06
    åĿ¡
    -0.05
    çIJ³å¨ľ
    -0.05
    æīĢ产çĶŁçļĦ
    -0.05
     Brace
    -0.05
    POSITIVE LOGITS
    oller
    0.10
    åIJİéĢĢ
    0.08
    озÑıй
    0.08
    bürger
    0.08
    getti
    0.08
    GORITH
    0.08
    ghan
    0.08
    èħĨ
    0.08
    baum
    0.08
    Ñıд
    0.08
    Activations Density 0.001%

    No Known Activations