© 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. 17999
    Prev
    Next
    INDEX
    Explanations

    class definitions in code

    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
    ÑģÑı
    -0.06
    ÙĦ
    -0.06
    er
    -0.06
    body
    -0.06
    ed
    -0.05
    dav
    -0.05
    é¢ĺ为
    -0.05
    chy
    -0.05
    ä½ĵèĥ½
    -0.05
    en
    -0.05
    POSITIVE LOGITS
    adio
    0.07
    unct
    0.06
    unft
    0.06
    اتÙĩ
    0.06
    ago
    0.06
    aries
    0.06
    Referensi
    0.06
    ulto
    0.06
    weep
    0.06
    abbo
    0.06
    Activations Density 0.007%

    No Known Activations