© 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. 21342
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE `id`

    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
    sonian
    -0.07
    ooth
    -0.06
    æĭ³
    -0.06
    plen
    -0.06
    rag
    -0.06
     geweest
    -0.06
    ehl
    -0.06
    thes
    -0.05
    quilib
    -0.05
    lieg
    -0.05
    POSITIVE LOGITS
    ä¸ļåįıä¼ļ
    0.06
    åĨħåľ¨
    0.05
    许
    0.05
    帼
    0.05
    ener
    0.05
    OP
    0.05
    æ³ķå¾ĭä¿ĿæĬ¤
    0.05
    -in
    0.05
    eneral
    0.05
    éĹŃ
    0.05
    Activations Density 0.009%

    No Known Activations