© 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. 22163
    Prev
    Next
    INDEX
    Explanations

    categories and tags

    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
    ature
    -0.05
    dsm
    -0.05
    ial
    -0.05
    åħ³æ³¨
    -0.05
    æĽ´å¤ļåħ³äºİ
    -0.05
    ÅĻ
    -0.05
    ess
    -0.05
    aisin
    -0.05
    ä¸ĢçĤ¹åĦ¿
    -0.05
    apkan
    -0.05
    POSITIVE LOGITS
    skirts
    0.07
    uarte
    0.07
    deaux
    0.06
    æ±Ľ
    0.06
    à¸ģัà¸ļà¸ģาร
    0.06
    弧度
    0.06
    shipment
    0.06
     ath
    0.06
    ëĭī
    0.06
    æ¢ħæŀĹ
    0.06
    Activations Density 0.001%

    No Known Activations