© 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. 25521
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing, -tion, -ology, -ship, -ncy

    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
    ave
    -0.07
    unek
    -0.07
    ibel
    -0.07
    amac
    -0.07
    beck
    -0.06
    unge
    -0.06
     Sting
    -0.06
     personalmente
    -0.06
    ange
    -0.06
    quito
    -0.06
    POSITIVE LOGITS
    ermen
    0.08
    æľºç¼ĺ
    0.08
    å¸Ī大
    0.08
    erg
    0.07
    çłĶ讨ä¼ļ
    0.07
    Impossible
    0.07
    erd
    0.07
    eny
    0.07
    ncia
    0.06
    tea
    0.06
    Activations Density 0.862%

    No Known Activations