© 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. 23645
    Prev
    Next
    INDEX
    Explanations

    journal letters

    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
     gul
    -0.07
    ickl
    -0.06
    ä¸Ģçķª
    -0.06
    iku
    -0.06
    åįģä¸īç«ł
    -0.06
     né
    -0.06
    né
    -0.06
    oxic
    -0.06
    odus
    -0.06
    ouched
    -0.06
    POSITIVE LOGITS
    åľ°ä¹ħ
    0.07
     Ga
    0.07
    eil
    0.07
    WithType
    0.07
    Ga
    0.07
    åķĨåĬ¡åIJĪä½ľ
    0.07
    åŀĥåľ¾å¤ĦçIJĨ
    0.07
    ¤íĹ
    0.07
    ãĥ³ãĤ°
    0.07
    èĻij
    0.07
    Activations Density 0.005%

    No Known Activations