© 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. 22589
    Prev
    Next
    INDEX
    Explanations

    tech path keywords

    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
    rosso
    -0.07
    aca
    -0.06
    ostro
    -0.06
    chenkt
    -0.06
     synthetic
    -0.06
    estra
    -0.05
     ÙĪراء
    -0.05
     hird
    -0.05
    ÙĨج
    -0.05
     adverts
    -0.05
    POSITIVE LOGITS
    ipo
    0.07
    åģı
    0.06
     lam
    0.05
    up
    0.05
    çĻ¾
    0.05
    spr
    0.05
    Tier
    0.05
    æ§ĺãģ«
    0.05
    lam
    0.05
    æ»ij
    0.05
    Activations Density 0.191%

    No Known Activations