© 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. 24027
    Prev
    Next
    INDEX
    Explanations

    ending in ful or lessly

    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
    ä¸ī个åŃĹ
    -0.07
    aliza
    -0.07
    IZE
    -0.07
    è´¨çļĦ
    -0.07
    hia
    -0.07
    hets
    -0.07
    lando
    -0.07
    alité
    -0.07
    ipro
    -0.07
    alidade
    -0.07
    POSITIVE LOGITS
    fulness
    0.09
    upon
    0.09
     upon
    0.08
     Upon
    0.08
    ersh
    0.08
    fully
    0.08
    ä½ķå¤Ħ
    0.07
    lessly
    0.07
    ful
    0.07
    angan
    0.07
    Activations Density 0.287%

    No Known Activations