© 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. 29799
    Prev
    Next
    INDEX
    Explanations

    end of line delimiters

    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
    zep
    -0.07
    enames
    -0.07
    Anywhere
    -0.07
    å·®ãģĹ
    -0.07
    ewater
    -0.07
    åºĶå½ĵä¾Ŀçħ§
    -0.07
    ismo
    -0.07
    æī¹ç¤º
    -0.06
    ä»Ģä¹Īåľ°æĸ¹
    -0.06
    otty
    -0.06
    POSITIVE LOGITS
    赫çĦ¶
    0.08
    nost
    0.07
    å®ķ
    0.07
    çĴŀ
    0.07
    ublic
    0.06
    rone
    0.06
    太ä»ĵ
    0.06
    stin
    0.06
    çļĩåŁİ
    0.06
    ulty
    0.06
    Activations Density 0.014%

    No Known Activations