© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19761
    Prev
    Next
    INDEX
    Explanations

    the one

    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
    utzen
    -0.07
    verkauf
    -0.07
    tage
    -0.07
    chino
    -0.07
    enje
    -0.07
    rium
    -0.07
    èĦ±é¢ĸ
    -0.07
     fiat
    -0.07
    hurt
    -0.07
    новÑĮ
    -0.07
    POSITIVE LOGITS
    ed
    0.06
    led
    0.05
    ongo
    0.05
    br
    0.05
    çŃīåľ°
    0.05
     оÑĤлиÑĩ
    0.05
    ness
    0.05
    赤水
    0.05
    æĽ¿
    0.04
    кала
    0.04
    Activations Density 0.006%

    No Known Activations