© 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. 30767
    Prev
    Next
    INDEX
    Explanations

    punctuation, followed by She, Thank, or To

    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
     thus
    -0.07
    ä½Ĩæĺ¯
    -0.07
    ä½Ĩæĺ¯ä»ĸ们
    -0.06
    ä½Ĩæĺ¯æĪij们
    -0.06
    owitz
    -0.06
    apt
    -0.06
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.06
    way
    -0.06
    stein
    -0.06
    ä½Ĩæĺ¯è¿Ļ个
    -0.06
    POSITIVE LOGITS
    esub
    0.09
    nameof
    0.08
    entak
    0.08
    æĸ°åĮĹ
    0.07
    çŃīçĿĢä½ł
    0.07
     ÑģамоÑĥпÑĢав
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    åĮĹåIJij
    0.07
    æ´²
    0.07
    skem
    0.07
    Activations Density 0.006%

    No Known Activations