© 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. 62206
    Prev
    Next
    INDEX
    Explanations

    yet or ainda

    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
    ihan
    -0.08
    ãĤ¤ãĥī
    -0.08
     latter
    -0.08
    ael
    -0.08
     ulang
    -0.08
    éĺħ读åİŁæĸĩ
    -0.07
    /proto
    -0.07
    毫ä¸įçĬ¹è±«
    -0.07
    alement
    -0.07
    isty
    -0.07
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.10
     nữa
    0.09
    çŃīä»Ģä¹Ī
    0.09
    åħ¶ä»ĸçļĦ
    0.08
    oop
    0.08
    åĪ«çļĦ
    0.08
    äºĽä»Ģä¹Ī
    0.08
    äºĽå¹´
    0.08
    ame
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    Activations Density 0.007%

    No Known Activations