© 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. 61988
    Prev
    Next
    INDEX
    Explanations

    .com domains

    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
    ibase
    -0.07
     Wheeler
    -0.07
    ATRIX
    -0.07
    aza
    -0.07
     Bernstein
    -0.07
    ász
    -0.07
    ÖĢ
    -0.07
    abilitas
    -0.06
     NONINFRINGEMENT
    -0.06
    说æĺ¯
    -0.06
    POSITIVE LOGITS
    oute
    0.07
    åħ«è¾¾
    0.07
    åĵģ
    0.07
     Comic
    0.07
     Espe
    0.06
    å§ĵ
    0.06
    ä¸ĩå¥Ĺ
    0.06
    ãĤ«ãĥIJãĥ¼
    0.06
    å¦Ĥçİī
    0.06
    åıĺæĽ´è®°å½ķ
    0.06
    Activations Density 0.013%

    No Known Activations