© 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. 21254
    Prev
    Next
    INDEX
    Explanations

    buy or purchase

    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
     w
    -0.06
    epass
    -0.06
    ,
    -0.05
    ↵
    -0.05
    +w
    -0.05
    ware
    -0.05
     de
    -0.05
     a
    -0.05
    runner
    -0.05
     run
    -0.05
    POSITIVE LOGITS
    kota
    0.07
    IALIZ
    0.07
     Eag
    0.06
    qip
    0.06
    olong
    0.06
    antar
    0.06
     horarios
    0.06
     MOZ
    0.06
    strup
    0.06
    laz
    0.06
    Activations Density 0.002%

    No Known Activations