© 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. 21895
    Prev
    Next
    INDEX
    Explanations

    here’s

    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
    ottes
    -0.07
    ebilecek
    -0.06
    otte
    -0.06
    omat
    -0.06
    "%(
    -0.06
     permalink
    -0.06
     bot
    -0.06
    pute
    -0.06
    -0.06
    avel
    -0.06
    POSITIVE LOGITS
    2
    0.06
    1
    0.05
    Å
    0.05
    禾
    0.05
    une
    0.05
    ç³»ç»ŁçļĦ
    0.05
    åѤ
    0.05
     Sight
    0.04
     desidera
    0.04
    åİħ
    0.04
    Activations Density 0.003%

    No Known Activations