© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21282
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ics' or 'ation'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸä¸İ
    -0.06
    icoli
    -0.06
     chói
    -0.05
    ick
    -0.05
    builtin
    -0.05
    æŁIJç§į
    -0.05
    åı¯èĥ½ä¼ļ被
    -0.05
     rivolta
    -0.05
    ummer
    -0.05
    Hopefully
    -0.05
    POSITIVE LOGITS
    onces
    0.06
    rus
    0.06
    çĸ¹
    0.06
    appelle
    0.06
    åİ
    0.05
     prem
    0.05
    mac
    0.05
    ked
    0.05
    ostas
    0.05
    оло
    0.05
    Activations Density 0.016%

    No Known Activations