© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18497
    Prev
    Next
    INDEX
    Explanations

    quotations and special characters

    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
    æ»
    -0.06
    etical
    -0.05
    ÃŃs
    -0.05
     und
    -0.05
    -0.05
    ↵
    -0.05
    ÙģÙĬض
    -0.05
    etro
    -0.05
     Regents
    -0.05
    <|endoftext|>
    -0.04
    POSITIVE LOGITS
    werben
    0.08
    ingend
    0.06
    entras
    0.06
    umus
    0.06
    ÑĤÑıги
    0.06
    ÏĬ
    0.06
    ãģ¨ãģĦãģ£ãģ¦
    0.06
    помним
    0.06
    ationally
    0.06
    åĪĽå»ºå·¥ä½ľ
    0.06
    Activations Density 0.016%

    No Known Activations