© 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. 18051
    Prev
    Next
    INDEX
    Explanations

    reincarnationKarma Yoga

    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
    alom
    -0.08
     rady
    -0.07
    Inset
    -0.07
    omp
    -0.07
    voie
    -0.07
    alang
    -0.07
    verture
    -0.07
    gris
    -0.06
    prech
    -0.06
    egah
    -0.06
    POSITIVE LOGITS
    è½®åĽŀ
    0.07
     next
    0.06
    循çݯ
    0.06
    ä¸ĭ次
    0.06
     Next
    0.06
    ä¸ĭä¸Ģ次
    0.05
    next
    0.05
     i
    0.05
    ä¸ĭä¸Ģ
    0.05
     interv
    0.05
    Activations Density 0.002%

    No Known Activations