© 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. 32374
    Prev
    Next
    INDEX
    Explanations

    legal cases (F.2d)

    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
    rd
    -0.08
    uard
    -0.07
    \.
    -0.07
     khuôn
    -0.07
    asz
    -0.07
    ober
    -0.06
    åıĺ
    -0.06
    æŀī
    -0.06
    é»ĦçīĽ
    -0.06
    åĬ¹
    -0.06
    POSITIVE LOGITS
    جر
    0.10
    erable
    0.08
    erval
    0.08
    erate
    0.07
    azza
    0.07
    å¾ģ
    0.07
    山大
    0.06
    _hostname
    0.06
    åħ¨éĿ¢å»ºæĪIJ
    0.06
    lify
    0.06
    Activations Density 0.016%

    No Known Activations