© 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. 16867
    Prev
    Next
    INDEX
    Explanations

    list separators and numbers

    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
    adena
    -0.07
     resa
    -0.06
    trup
    -0.06
    erez
    -0.06
     ÙĪعÙĨ
    -0.06
    ä¹ĭéķ¿
    -0.06
     cóm
    -0.06
    icity
    -0.06
    rete
    -0.06
     tulev
    -0.06
    POSITIVE LOGITS
    dz
    0.06
     dec
    0.05
     ones
    0.05
    min
    0.05
     min
    0.05
     v
    0.05
    度è¿ĩ
    0.05
    庶
    0.05
    cent
    0.05
     suatu
    0.05
    Activations Density 0.003%

    No Known Activations