© 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. 18226
    Prev
    Next
    INDEX
    Explanations

    singleton adults primary national individual data

    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
    /Framework
    -0.06
    ä¼łåĩº
    -0.06
    egis
    -0.06
    rug
    -0.06
    Backing
    -0.06
    ommage
    -0.06
    ecie
    -0.06
    itat
    -0.06
    assis
    -0.05
    ç¢İäºĨ
    -0.05
    POSITIVE LOGITS
    g
    0.05
    å±±èį¯
    0.05
    æĥ³åľ¨
    0.05
    æĥ³åĪ°è¿ĻéĩĮ
    0.05
    oria
    0.05
    chim
    0.05
    "
    0.05
     Ñĥпа
    0.05
    ph
    0.05
    'in
    0.05
    Activations Density 0.285%

    No Known Activations