© 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. 19193
    Prev
    Next
    INDEX
    Explanations

    each other

    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
    istine
    -0.09
    ä¿¡æģ¯çĶ±
    -0.08
    èī²åĪĹ
    -0.08
    ulette
    -0.08
    ä¹ĭ梦
    -0.08
    λÏİ
    -0.08
     dentre
    -0.08
    ÙĪاÙĨÙĬ
    -0.08
    为主ä½ĵçļĦ
    -0.07
    ÙĦÙĤÙī
    -0.07
    POSITIVE LOGITS
     ниÑħ
    0.10
     them
    0.07
    شاÙĨ
    0.07
     اÙĦبعض
    0.07
    è¾Ī
    0.07
    -caption
    0.07
    haj
    0.07
    hout
    0.06
    amp
    0.06
    輩
    0.06
    Activations Density 0.018%

    No Known Activations