© 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. 22377
    Prev
    Next
    INDEX
    Explanations

    incident reporting

    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
     (
    -0.05
    imed
    -0.05
     not
    -0.05
    astre
    -0.05
     Google
    -0.05
     natural
    -0.05
    åħ¬
    -0.05
     null
    -0.05
     bi
    -0.05
    è¾Ł
    -0.05
    POSITIVE LOGITS
    esor
    0.06
    åį§
    0.06
    upert
    0.06
    len
    0.06
    ipher
    0.06
    _=
    0.06
    èĩ¥
    0.06
    iace
    0.06
    еÑĢÑĤ
    0.06
     eskort
    0.06
    Activations Density 0.009%

    No Known Activations