© 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. 16588
    Prev
    Next
    INDEX
    Explanations

    zero counts or percentages

    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
    çĦķçĦ¶
    -0.07
    åłĤåłĤ
    -0.07
    åİŁæĸĩåĩºå¤Ħ
    -0.07
    ÙĬرة
    -0.07
    æĮģä¹ĭ以
    -0.07
    åĬ¡
    -0.06
     séqu
    -0.06
     toJSON
    -0.06
    å®°
    -0.06
    ä¸įæĺĵ
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.10
    /no
    0.08
    laps
    0.08
    (no
    0.08
    asket
    0.08
    èĩŃ
    0.08
    egin
    0.07
    educt
    0.07
    èµı
    0.07
    .empty
    0.07
    Activations Density 0.022%

    No Known Activations