© 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. 22528
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis )

    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
     cumul
    -0.06
    zzle
    -0.06
    zero
    -0.06
    esel
    -0.06
    erma
    -0.06
    ectores
    -0.06
     ZERO
    -0.06
    çĻ¾ç§ijåħ¨ä¹¦
    -0.06
    mens
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
    pac
    0.06
    weig
    0.05
    bolehkan
    0.05
    assis
    0.05
    éĩij鸡
    0.05
    imis
    0.05
     heels
    0.04
    æ¡IJ
    0.04
     arising
    0.04
     el
    0.04
    Activations Density 0.003%

    No Known Activations