© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22374
    Prev
    Next
    INDEX
    Explanations

    up-to-date

    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
    Negative Logits
    teria
    -0.07
    ÑģлÑĮ
    -0.07
    Ø©
    -0.07
    skich
    -0.07
    sium
    -0.06
     geometr
    -0.06
    utdown
    -0.06
    als
    -0.06
    ersion
    -0.06
    ä¸ĭæĮ«
    -0.06
    POSITIVE LOGITS
    emn
    0.06
    ŀ
    0.06
    osz
    0.06
    常å§Ķ
    0.05
    emps
    0.05
    à®Ļà¯įà®ķ
    0.05
    uish
    0.05
    emm
    0.05
    oom
    0.05
     Feinstein
    0.05
    Activations Density 0.007%

    No Known Activations