© 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. 41510
    Prev
    Next
    INDEX
    Explanations

    from a

    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
    æĺ¯ä½łä»¬
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    bery
    -0.07
    :normal
    -0.07
    alej
    -0.07
    piel
    -0.07
    ÏĢαν
    -0.07
     tedy
    -0.07
    é¾ĻèĻİ
    -0.07
    å®ŀè¯Ŀ
    -0.07
    POSITIVE LOGITS
    ä¸Ģ个åı«
    0.10
    åĪ°ä¸Ģ个
    0.10
     predefined
    0.10
    è¿ĩä¸Ģ个
    0.09
    ç§°ä½ľ
    0.09
     designated
    0.09
    称为
    0.09
    çĿĢä¸Ģ个
    0.09
    å°ĤçĶ¨ãģ®
    0.08
    åĪ°äºĨä¸Ģ个
    0.08
    Activations Density 0.561%

    No Known Activations