© 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. 21341
    Prev
    Next
    INDEX
    Explanations

    repeated 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
    ä»Ķç»ĨçļĦ
    -0.06
    IRD
    -0.06
    haal
    -0.05
    pit
    -0.05
    =”
    -0.05
    ÑĥÑīеÑģÑĤво
    -0.05
    aturen
    -0.05
    éĩįåŀĭ
    -0.05
    лав
    -0.05
    åı¯æĥ³
    -0.05
    POSITIVE LOGITS
    çīĪ
    0.06
    ief
    0.06
    qi
    0.05
    ç³
    0.05
    ibr
    0.05
    zos
    0.05
    stars
    0.05
    udios
    0.05
     Mona
    0.05
    auptsächlich
    0.05
    Activations Density 0.001%

    No Known Activations