© 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. 21377
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and items

    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
    ↵
    -0.07
     po
    -0.05
    ane
    -0.05
    pr
    -0.05
     ut
    -0.05
     pe
    -0.05
    proof
    -0.05
     fa
    -0.05
    nt
    -0.05
     sk
    -0.05
    POSITIVE LOGITS
     contactez
    0.07
    taki
    0.07
    åħ®
    0.07
    Äĩa
    0.07
     vorba
    0.07
    að
    0.07
    itionally
    0.07
    已累计
    0.07
    Äĩu
    0.06
    ventura
    0.06
    Activations Density 0.018%

    No Known Activations