© 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. 22192
    Prev
    Next
    INDEX
    Explanations

    experts and surrounding words

    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
    /d
    -0.05
     d
    -0.05
    uum
    -0.05
     Ñĩего
    -0.05
    à¹Ģà¸ģาะ
    -0.05
    ek
    -0.05
    onical
    -0.05
    /dr
    -0.04
     gran
    -0.04
     едини
    -0.04
    POSITIVE LOGITS
    zinho
    0.09
    ingly
    0.08
    ly
    0.08
    زة
    0.08
    æĥħåĨµä¸ĭ
    0.07
    tility
    0.07
    ÙħÙĬ
    0.07
    вига
    0.07
    rett
    0.07
    entially
    0.07
    Activations Density 0.005%

    No Known Activations