© 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. 32005
    Prev
    Next
    INDEX
    Explanations

    ending in a number

    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
     Jakob
    -0.07
    ä½łçļĦ人
    -0.07
    æĺİ亮
    -0.07
    iak
    -0.07
    ittel
    -0.07
    ubre
    -0.06
    渺
    -0.06
    åªĴ
    -0.06
    acl
    -0.06
    oice
    -0.06
    POSITIVE LOGITS
    ç»ĵå°¾
    0.12
     ending
    0.08
    æĶ¶å°¾
    0.08
     endings
    0.08
    terminal
    0.08
    ç»ĵæĿŁæŶ
    0.08
     terminal
    0.08
    ç»ĵæĿŁ
    0.08
    æľ«
    0.08
    véd
    0.07
    Activations Density 0.007%

    No Known Activations