© 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. 17948
    Prev
    Next
    INDEX
    Explanations

    conditions or restrictions

    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
    墳
    -0.07
    åĿŁ
    -0.07
     confron
    -0.07
    awai
    -0.06
    ionado
    -0.06
    weed
    -0.06
     **:**
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    Ouest
    -0.06
    esión
    -0.06
    POSITIVE LOGITS
    en
    0.05
    容积
    0.05
     миÑĢ
    0.05
    ables
    0.05
    holm
    0.05
     immortal
    0.05
     unchanged
    0.05
    .html
    0.05
    erc
    0.05
    å¾ĹäºĨ
    0.05
    Activations Density 0.004%

    No Known Activations