© 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. 21512
    Prev
    Next
    INDEX
    Explanations

    "Per se"

    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
    æijĺèĩª
    -0.06
    atz
    -0.06
    鼨åIJİ
    -0.06
    åı¯èĥ½ä¼ļåĩºçİ°
    -0.06
    åĴĮåĽ¾çīĩ
    -0.06
    que
    -0.06
    è§Ĥ
    -0.05
    ä¸ĩåį·
    -0.05
    åIJ¯çĶ¨
    -0.05
    upi
    -0.05
    POSITIVE LOGITS
    ãĤĦãģ¯
    0.09
    %A
    0.08
    åĪ¤
    0.08
    سÙĪب
    0.08
    æld
    0.08
    бай
    0.08
    lieder
    0.07
     %-
    0.07
    chetti
    0.07
    åħļçļĦäºĮåįģ大
    0.07
    Activations Density 0.004%

    No Known Activations