© 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. 16719
    Prev
    Next
    INDEX
    Explanations

    height followed by a colon

    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
     lan
    -0.05
     Guth
    -0.05
     impact
    -0.05
     effect
    -0.05
     standalone
    -0.05
    fern
    -0.05
    ou
    -0.05
    段
    -0.05
     differently
    -0.05
    itives
    -0.05
    POSITIVE LOGITS
    zos
    0.07
    NOP
    0.06
    wd
    0.06
    Ļ
    0.06
    upal
    0.06
    cratch
    0.06
    (Of
    0.06
    inds
    0.06
    èĵ®
    0.06
    ä¿ij
    0.06
    Activations Density 0.005%

    No Known Activations