© 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. 21519
    Prev
    Next
    INDEX
    Explanations

    random number generator

    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
    éļıæľº
    -0.07
     random
    -0.07
    æijĩåı·
    -0.06
     randomly
    -0.06
    =random
    -0.06
    plet
    -0.06
     ngẫu
    -0.06
    /random
    -0.06
    -random
    -0.06
     RANDOM
    -0.06
    POSITIVE LOGITS
    æ¯ı项
    0.05
    olute
    0.05
    ensive
    0.05
    è°Īç¬ij
    0.05
    éľĵ
    0.05
    ains
    0.05
    åİĭ
    0.05
    ода
    0.05
    éŨåħ³
    0.05
    æī®
    0.05
    Activations Density 0.007%

    No Known Activations