© 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. 8865
    Prev
    Next
    INDEX
    Explanations

    court decisions

    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
    icat
    -0.08
    yno
    -0.07
    chor
    -0.07
    éŃĦ
    -0.07
    ç´§ç´§åľ°
    -0.07
    å°±åĥıä¸Ģ个
    -0.07
    æĦ
    -0.06
    ITHER
    -0.06
    /R
    -0.06
     Revenge
    -0.06
    POSITIVE LOGITS
    ове
    0.07
    mort
    0.07
    bler
    0.07
    ools
    0.06
    CustomAttributes
    0.06
     Fri
    0.06
    кÑĢо
    0.06
    åĢ¼å¾Ĺä¸Ģ
    0.06
     Stell
    0.06
    uiten
    0.06
    Activations Density 0.006%

    No Known Activations