© 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. 17248
    Prev
    Next
    INDEX
    Explanations

    the following

    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
    ar
    -0.08
    s
    -0.05
    unk
    -0.05
    ig
    -0.05
    æѤæŶ
    -0.05
    har
    -0.05
    f
    -0.05
    j
    -0.05
    Gr
    -0.05
    ...
    -0.05
    POSITIVE LOGITS
    lien
    0.07
    egis
    0.07
    emen
    0.07
    caster
    0.07
    casting
    0.07
    ever
    0.07
    itario
    0.06
     tá»ij
    0.06
    rage
    0.06
     sánh
    0.06
    Activations Density 0.028%

    No Known Activations