© 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. 18282
    Prev
    Next
    INDEX
    Explanations

    `tagged` or `'m` followed by text

    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
    æı´
    -0.06
    anners
    -0.06
    incontro
    -0.06
    ...*
    -0.05
    æĺİçĻ½
    -0.05
    hers
    -0.05
     honored
    -0.05
    illy
    -0.05
    è¿ĩä¸Ģ个
    -0.05
    unt
    -0.05
    POSITIVE LOGITS
    ihan
    0.07
     cả
    0.06
    rau
    0.06
    åħļçļĦ
    0.05
    аве
    0.05
    egi
    0.05
    iori
    0.05
    alde
    0.05
    sey
    0.05
    å®´
    0.05
    Activations Density 0.001%

    No Known Activations