© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18234
    Prev
    Next
    INDEX
    Explanations

    self-conscious, concerned, psychosocial

    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
    ember
    -0.06
    åħģ
    -0.05
    æ¡Ī
    -0.05
     Assignment
    -0.05
    åĪĿ
    -0.05
    avour
    -0.05
     Ech
    -0.05
    认
    -0.05
     ech
    -0.05
    dex
    -0.05
    POSITIVE LOGITS
    ayos
    0.06
    鬣
    0.06
    æĪĸ许æľī
    0.06
    اÙĪÙģ
    0.05
    ä¸ĢçĦ¡
    0.05
    aways
    0.05
    .newArrayList
    0.05
    åĨįæĹł
    0.05
    åĽłæĩī
    0.05
    ’S
    0.05
    Activations Density 0.001%

    No Known Activations