© 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. 17447
    Prev
    Next
    INDEX
    Explanations

    I have

    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
    ice
    -0.06
     lest
    -0.06
    ew
    -0.05
    ese
    -0.05
    upan
    -0.05
     ing
    -0.05
    olar
    -0.05
     Un
    -0.05
     *
    -0.05
    åĬłå¼ºåŃ¦ä¹ł
    -0.05
    POSITIVE LOGITS
    guer
    0.07
    à¸Ħำà¸Ļว
    0.07
     melew
    0.07
    bahan
    0.06
    عاÙĦ
    0.06
    gur
    0.06
    loo
    0.06
    gelopen
    0.06
    .argv
    0.06
    teria
    0.06
    Activations Density 0.080%

    No Known Activations