© 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. 18334
    Prev
    Next
    INDEX
    Explanations

    for information or details

    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
    inaldo
    -0.06
     unknow
    -0.06
     اÙĦÙĨات
    -0.06
     disert
    -0.06
    åį¡è¥¿
    -0.06
     inexp
    -0.06
    ä¹Łä¸įçŁ¥éģĵ
    -0.06
    nés
    -0.06
    ä¸įçŁ¥
    -0.06
    ÑĤеÑĢо
    -0.06
    POSITIVE LOGITS
    POINTS
    0.05
    Lists
    0.05
    å½ķ
    0.05
     points
    0.05
    oug
    0.05
     of
    0.04
    å¼ķ
    0.04
    points
    0.04
     lif
    0.04
    itical
    0.04
    Activations Density 0.020%

    No Known Activations