© 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. 19271
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    erno
    -0.06
    en
    -0.05
    ities
    -0.05
    ä¸įçĦ¶
    -0.05
    ernen
    -0.05
    {
    -0.05
    av
    -0.05
    aup
    -0.05
    ly
    -0.05
    enburg
    -0.05
    POSITIVE LOGITS
    ingly
    0.08
    itecture
    0.08
    ed
    0.08
    embali
    0.07
    eterangan
    0.07
    ذج
    0.07
    halb
    0.07
    eko
    0.07
    edy
    0.07
    edic
    0.07
    Activations Density 0.000%

    No Known Activations