© 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. 20391
    Prev
    Next
    INDEX
    Explanations

    quaternary

    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
    æīĢåIJij
    -0.08
    μον
    -0.08
    åIJĮæĹ¶ä¹Łè¦ģ
    -0.07
    outs
    -0.07
     Lieu
    -0.07
    ä¸īéĥ¨æĽ²
    -0.07
    å°ıéĺŁ
    -0.07
    indow
    -0.07
    翼翼
    -0.07
    ç©«
    -0.07
    POSITIVE LOGITS
    pil
    0.07
    åĽ½å®¶ä¸Ģ级
    0.07
    Ī
    0.07
    Evt
    0.07
    /embed
    0.07
    stv
    0.07
    רת
    0.06
    /full
    0.06
    heng
    0.06
    rech
    0.06
    Activations Density 0.004%

    No Known Activations