© 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. 20031
    Prev
    Next
    INDEX
    Explanations

    past experiences or events

    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
    uid
    -0.05
    rs
    -0.05
     nov
    -0.05
    ingham
    -0.05
    æłĭ
    -0.05
    ir
    -0.05
    aid
    -0.05
    on
    -0.05
    head
    -0.04
    un
    -0.04
    POSITIVE LOGITS
    ",$
    0.07
    æĪijä¹Łåİ»
    0.07
    neys
    0.06
    truk
    0.06
    qli
    0.06
    ney
    0.06
    宿
    0.06
    èī²åĪĹ
    0.06
    è¿ijçļĦ
    0.06
    æ´²
    0.06
    Activations Density 0.004%

    No Known Activations