© 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. 18157
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    游
    -0.05
     invol
    -0.05
    ÑĭÑħ
    -0.05
    )
    -0.05
    пей
    -0.05
     brig
    -0.05
    ook
    -0.05
    ptic
    -0.05
    æ´¾åĩº
    -0.05
    ves
    -0.05
    POSITIVE LOGITS
    AMY
    0.06
    æĩ¿
    0.06
    igare
    0.06
    cito
    0.06
    ucker
    0.06
     ziem
    0.06
    åĩłçĤ¹
    0.06
    AGENT
    0.06
    èIJ½å®ŀåĪ°ä½į
    0.06
    igts
    0.06
    Activations Density 0.016%

    No Known Activations