© 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. 16958
    Prev
    Next
    INDEX
    Explanations

    spencer, his, followed by, owner, host, Emer, Kyle

    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
    ÙĪÙħاÙĨ
    -0.06
    arvi
    -0.05
    åĦ¿
    -0.05
    çĭĤ
    -0.05
    åħ±äº«
    -0.05
     complic
    -0.05
    Ø·ÙĬÙĨ
    -0.05
     intensive
    -0.05
    raga
    -0.05
    root
    -0.05
    POSITIVE LOGITS
    带ä¸Ĭ
    0.07
    .bd
    0.06
    emas
    0.06
    kow
    0.06
    nova
    0.06
    kozás
    0.06
    gå
    0.06
    testdata
    0.06
    acken
    0.06
    sher
    0.06
    Activations Density 0.001%

    No Known Activations