© 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. 16903
    Prev
    Next
    INDEX
    Explanations

    smooth surfaces or textures

    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
    .handle
    -0.06
    Ń
    -0.05
    ham
    -0.05
     glance
    -0.05
    iable
    -0.05
    èĸĦèĸĦçļĦ
    -0.05
     limp
    -0.05
    ÙĬÙĨ
    -0.05
    arm
    -0.05
    on
    -0.05
    POSITIVE LOGITS
    ãģĦãĤĭ
    0.08
    sab
    0.07
    s
    0.07
    ÑĢÑıдÑĥ
    0.07
    çijĻ
    0.07
    ség
    0.07
    nok
    0.07
    sz
    0.06
    ancock
    0.06
    skins
    0.06
    Activations Density 0.004%

    No Known Activations