© 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. 14307
    Prev
    Next
    INDEX
    Explanations

    taken six

    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
    ÑĤÑĮÑİ
    -0.09
    äºĴèģĶç½ijä¿¡æģ¯æľįåĬ¡
    -0.08
    åį«ä¸ľ
    -0.08
    对åIJĦ
    -0.08
    saan
    -0.08
    aat
    -0.08
    ãĥĥãĥĪ
    -0.08
    Insensitive
    -0.08
    è¡¥åĬ©è´¹
    -0.08
    obet
    -0.08
    POSITIVE LOGITS
    éĩİ
    0.07
    å²Ĺ
    0.07
    å±ħ
    0.06
    å°ı
    0.06
    Lab
    0.06
    iek
    0.06
    è¡Ģ
    0.06
    大
    0.06
    ħ
    0.06
     body
    0.06
    Activations Density 0.005%

    No Known Activations