© 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. 17017
    Prev
    Next
    INDEX
    Explanations

    working on

    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
    iar
    -0.07
    -INF
    -0.06
    med
    -0.05
    anol
    -0.05
     superf
    -0.05
    çIJĨåĮĸ
    -0.05
    ç»Ĩç»Ĩ
    -0.05
    -js
    -0.05
    ")));
    -0.05
    pto
    -0.05
    POSITIVE LOGITS
    agin
    0.07
    ä¼Ĺ
    0.06
    TES
    0.06
     forg
    0.06
    ucher
    0.05
    ÏĦοÏĤ
    0.05
    çľ¾
    0.05
    utos
    0.05
    obet
    0.05
    å°ĺ
    0.05
    Activations Density 0.001%

    No Known Activations