© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19780
    Prev
    Next
    INDEX
    Explanations

    spatial and directional prepositions

    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
    gul
    -0.06
    kam
    -0.06
    æĽ´å¤ļ精彩
    -0.06
    åŃĹ
    -0.06
    ır
    -0.06
    Sharper
    -0.06
    coded
    -0.05
    æ±Ĥç²¾
    -0.05
     ذخ
    -0.05
    /control
    -0.05
    POSITIVE LOGITS
    ä½³
    0.05
    åĭ¾
    0.05
    空缺
    0.05
    ä»Ģä¹Ī
    0.05
    çľĭå¾Ĺ
    0.05
     Fon
    0.05
     réun
    0.05
    appendTo
    0.05
    à¸ĵ
    0.05
    ooks
    0.05
    Activations Density 0.001%

    No Known Activations