© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19476
    Prev
    Next
    INDEX
    Explanations

    should be

    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
    us
    -0.06
    /
    -0.06
    inte
    -0.05
    o
    -0.05
     contrast
    -0.05
     shaped
    -0.05
    int
    -0.05
     implic
    -0.05
    (
    -0.05
    ler
    -0.04
    POSITIVE LOGITS
    hium
    0.07
    дам
    0.07
    нÑıÑĤÑĮ
    0.07
    zana
    0.07
    åķĨéĵ¶è¡Į
    0.07
    elm
    0.07
    足以
    0.06
    ,eg
    0.06
     uom
    0.06
    ingo
    0.06
    Activations Density 0.032%

    No Known Activations