© 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. 22357
    Prev
    Next
    INDEX
    Explanations

    above normal, prove otherwise

    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
    åĵĪ
    -0.05
    uplic
    -0.05
    âĪ
    -0.05
    ety
    -0.05
    éĥ¨åĪĨ
    -0.05
    ï¼Ľ
    -0.05
    ï¼Į
    -0.05
     integ
    -0.05
    çİ°
    -0.04
    åıĬåħ¶
    -0.04
    POSITIVE LOGITS
    irken
    0.09
    èĢĮæĹł
    0.08
     while
    0.08
    èĢĮæľª
    0.07
    while
    0.07
    èĢĮ没æľī
    0.07
    lav
    0.07
    assi
    0.07
    ÙĩÙĪد
    0.07
    èĢĮæĪij们
    0.07
    Activations Density 0.099%

    No Known Activations