© 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. 20097
    Prev
    Next
    INDEX
    Explanations

    code imports and identifiers

    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
    zwi
    -0.06
    bahn
    -0.06
    æĹłæŃ¢
    -0.06
    agas
    -0.06
    oteles
    -0.06
    zeg
    -0.06
    bjerg
    -0.06
    å«Į
    -0.06
     prévo
    -0.06
    raft
    -0.06
    POSITIVE LOGITS
    ril
    0.06
    pon
    0.05
    ullen
    0.05
    第åįģåĽĽ
    0.05
    pery
    0.05
    ÑĢемен
    0.05
    Ñĩи
    0.05
     اÙĨ
    0.05
    ulado
    0.05
    ä½ľåĩº
    0.05
    Activations Density 0.001%

    No Known Activations