© 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. 20824
    Prev
    Next
    INDEX
    Explanations

    special comment blocks

    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
    arga
    -0.08
    arah
    -0.07
     lá»ıng
    -0.07
    èĸĦèĸĦçļĦ
    -0.07
    NewLabel
    -0.07
    é¾Ļæ¹¾
    -0.07
    åį³åĪ°
    -0.07
    ÐłÐIJÐĴ
    -0.07
    åıijå±ķæ½ľåĬĽ
    -0.07
    åĨħ容çĶ±
    -0.07
    POSITIVE LOGITS
    åºŀ
    0.07
    æı´
    0.07
    çIJ¢
    0.07
    èĩ
    0.07
    elight
    0.06
    åĪ¤
    0.06
    åħī
    0.06
    以èĩªå·±çļĦ
    0.06
    ope
    0.06
    ixon
    0.06
    Activations Density 0.001%

    No Known Activations