© 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. 19124
    Prev
    Next
    INDEX
    Explanations

    citations and technical code

    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
    иÑģк
    -0.05
    winkel
    -0.05
    tain
    -0.05
    è¯Ħä»·æĮĩæłĩ
    -0.05
    meni
    -0.05
    laat
    -0.05
    prar
    -0.05
     wink
    -0.05
    bla
    -0.05
    车çĶ¨
    -0.05
    POSITIVE LOGITS
     Consolid
    0.06
    é¸¡æ¯Ľ
    0.06
     tri
    0.05
    ardia
    0.05
    Commerce
    0.05
    bam
    0.05
    ÙĥÙĪÙĨ
    0.05
    Collapsed
    0.05
    cob
    0.05
     гÑĢамоÑĤно
    0.05
    Activations Density 0.001%

    No Known Activations