© 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. 14551
    Prev
    Next
    INDEX
    Explanations

    IR group

    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
    деÑı
    -0.08
    åĬłèĸª
    -0.07
    éĢĥ亡
    -0.07
    è¡
    -0.07
    èģĶåIJĪåĪĽå§ĭ人
    -0.07
    大计
    -0.07
    åį«çĶŁå±Ģ
    -0.07
    )[-
    -0.07
    è¡¥ä¹ł
    -0.07
    å£°æľĽ
    -0.06
    POSITIVE LOGITS
    (___
    0.10
    \"
    0.09
    ____
    0.08
    åľ¨çİ°åľº
    0.08
    çİ°åľº
    0.08
     \"
    0.08
    ___
    0.08
    ä¸įå°ijäºİ
    0.08
    .\"
    0.08
    ＿＿
    0.08
    Activations Density 0.025%

    No Known Activations